Tygart Media

Author: Will Tygart

  • Skotdal’s Mosaic Apartments Is Going Up on Pacific Avenue: 102 Art-Infused Homes Are the Latest Chapter in Downtown Everett’s Buildout

    Skotdal’s Mosaic Apartments Is Going Up on Pacific Avenue: 102 Art-Infused Homes Are the Latest Chapter in Downtown Everett’s Buildout

    What is Mosaic Apartments in Everett? Mosaic is Skotdal Real Estate’s newest downtown Everett apartment development — a seven-story, 102-unit art-infused community at 1702 Pacific Avenue in the heart of downtown. The project, designed by Johnson Oaklief Architecture & Planning, was approved in August 2024 and is currently in construction. It features a 106-stall parking garage, EV charging stations, a fitness center, co-working space and club lounge, and public artwork on the building’s blank wall areas — celebrating Everett’s growing public art scene. Status: coming soon.

    If you have walked down Pacific Avenue in downtown Everett in the last six months, you have already seen Mosaic going up. The seven-story footprint at 1702 Pacific Ave is the latest addition to a Skotdal Real Estate downtown portfolio that already includes Peninsula, Library Place, Library Place South Stack, Aero, Marquee, Olympic Park, Colby Center, and the Port Gardner Collection — and it tells the same story the rest of the buildout has been telling: downtown Everett is no longer a place that has to convince anyone that more housing belongs here.

    The 102-unit count puts Mosaic in the same scale range as Skotdal’s other recent downtown work — bigger than Library Place South Stack’s nine homes, smaller than the Waterfront Place high-density block but planted firmly inside the urban grid, two blocks off the Hewitt Avenue spine. We checked in with the project this week and the bones are up, the artwork concept is approved, and Skotdal’s announced status is the magic two words every downtown watcher has been waiting for: coming soon.

    What the building actually is

    The numbers, in order:

    • 7 stories, the maximum that downtown Everett’s mixed-use zoning supports along this Pacific Avenue stretch.
    • 102 upscale apartment homes — Skotdal has described them as bright modern homes consistent with the company’s other downtown portfolio buildings.
    • 106-stall parking garage — slightly more than one stall per unit, which by Pacific Northwest urban-infill standards is generous. Most new Seattle multifamily projects in the same density band are closer to 0.7 stalls per unit.
    • EV charging stations — present from day one, not retrofitted.
    • Fitness center, co-working space, and club lounge — the amenities package that has become standard in mid-market downtown apartments in the post-COVID era, when remote work and hybrid schedules drove demand for at-home co-working space.
    • Public art on blank wall areas and a fifty-foot planter at the base of the blank wall facing Pacific Avenue, per the city design review.

    The architect on record is Johnson Oaklief Architecture & Planning, LLC, the firm that has handled several of Skotdal’s other downtown projects. Craig Skotdal is the applicant of record. The project received city approval in August 2024 and has been moving through construction since.

    Why Skotdal keeps building downtown

    Craig Skotdal’s family has been buying and building in Everett since 1968. Art and Marianne Skotdal made their first purchase that year, and the portfolio has grown steadily through a long-term-hold strategy. In 2004 the company shifted from repositioning existing assets to ground-up construction, and the Peninsula Apartments — the company’s first new-build downtown — set what is now the visual template for the rest of downtown Everett’s apartment stock: brick, art, ground-floor activation, and a deep amenity package.

    Mosaic continues that template with an explicit nod to Everett’s public art scene. The artwork-on-blank-walls approach is a design choice that runs through several of Skotdal’s other properties — Aero leans into aerospace iconography, Library Place uses bibliophile motifs throughout its hallways, and Marquee Apartments plays off the Village Theatre across the street with theater-themed design.

    The thesis behind this much investment from one family in one city is simple: downtown Everett is still pricing below comparable Seattle infill submarkets but is starting to deliver the same amenities, transit, and walkability. The 2028 Sound Transit Everett Link timeline, the September 2026 stadium groundbreaking, the Edgewater Bridge that opened April 28, and the growing list of downtown restaurants and food halls are all things that nudge rent comps up and make new construction pencil. Skotdal has been ahead of that curve for two decades and has the leases to prove it — Peninsula, Library Place, and Library Place South Stack have all consistently posted occupancy above 95 percent in recent quarters.

    How Mosaic fits into the broader downtown picture

    The downtown apartment supply story across 2025 and 2026 is one of acceleration. Just in the last 90 days the Waterfront & Development desk has covered: the Sage Investment Group conversion of the 9602 19th Street SE Econo Lodge to 124 studios (Phase 1 leasing August 2026); the Millwright District Phase 2’s 300-plus apartment count breaking ground; Waterfront Place’s Sawyer and Carling buildings posting 95-percent occupancy with $2,202-to-$2,800 premium rents holding through a softer overall county market; and a $640 million Snohomish County apartment investment year per Kidder Mathews and The Registry that doubled from the 2023 trough.

    Mosaic plays in a different slice. It is not waterfront, it is not an income-restricted conversion, it is not a missing-middle play. It is upper-middle-market downtown urban infill — the slice that historically had to push out to Bellevue or downtown Seattle to find a building that pencils. The 102-unit count is large enough to move the downtown rent comp set but not so large that it floods the submarket the way the Waterfront Place high-density block did.

    When Mosaic delivers — Skotdal has not published a specific opening date yet beyond the “coming soon” status — it will join a downtown apartment portfolio in which a single private operator (Skotdal) is responsible for somewhere north of 600 units across nine buildings within roughly a 10-block walk. That kind of consolidated ownership is rare for a city of Everett’s size and has been a deliberate strategy: Skotdal’s leasing pages and tenant portal funnel residents across the portfolio, and amenities (fitness, co-working, the rooftop deck at Aero) are shared marketing across the buildings.

    What this means for downtown rents and street life

    Two predictions worth tracking once Mosaic delivers:

    1. Pacific Avenue ground-floor activation. The Pacific Avenue stretch between Hewitt Ave and the Everett Public Library has been a quieter retail block than Colby or Hewitt themselves. A 102-unit building with concentrated foot traffic at the entrance is the kind of thing that gives a small ground-floor retail bay or cafe space a real shot. Skotdal’s pattern at other buildings (the Library Place ground-floor activation, the Aero retail at street level) suggests Mosaic will follow that playbook.

    2. Downtown rent floor. Library Place and South Stack rents have been comping at $2.45 to $2.80 per square foot for upper units. Mosaic’s amenity package — fitness center, co-working, club lounge, EV charging, the 106-stall garage — is consistent with that band. If the building leases at that range from delivery, it will reinforce the floor that Skotdal’s other downtown buildings have established. If it has to come in below that to fill 102 units in a stiffer rental market, it will signal something different about where downtown Everett rents settle for the next cycle.

    The bigger picture is one Will has been writing about for months: downtown Everett is building the housing stock to actually be a city center. Not a suburb of Seattle. Not a stop on the way to the Mukilteo ferry. A city center. Mosaic is one more brick in that argument.

    Frequently Asked Questions

    Where is Mosaic Apartments being built in Everett?
    Mosaic is being built at 1702 Pacific Avenue in downtown Everett, WA 98201. The seven-story building sits on Pacific Avenue in the heart of the downtown commercial district, within a short walk of Hewitt Avenue and the Everett Public Library.

    How many units does Mosaic Apartments have?
    The building is a seven-story, 102-unit apartment community. It also includes a 106-stall parking garage.

    Who is developing Mosaic Apartments?
    Skotdal Real Estate is the developer, with Craig Skotdal as applicant of record. The project architect is Johnson Oaklief Architecture & Planning, LLC. The project received City of Everett approval in August 2024.

    When will Mosaic Apartments open in Everett?
    Skotdal has listed the project as “coming soon” with construction underway. The company has not published a specific opening date as of May 2026. Mosaic is the company’s newest downtown Everett development.

    What amenities does Mosaic Apartments offer?
    Mosaic’s announced amenity package includes EV charging stations, a fitness center, a co-working space and club lounge, and a 106-stall parking garage. The building also features public artwork on blank wall areas and a fifty-foot planter at the base of the Pacific Avenue facade, celebrating Everett’s public art scene.

    What other apartment buildings does Skotdal Real Estate own in Everett?
    Skotdal’s downtown Everett multifamily portfolio includes Peninsula Apartments, Library Place, Library Place South Stack, Aero Apartments, Marquee Apartments, Olympic Park Apartments, the Port Gardner Collection, and The Residences at Colby Center. The company has been buying and building in Everett since 1968 and shifted to ground-up new construction in 2004 with the Peninsula Apartments.

    Why does Mosaic emphasize public art?
    Mosaic is positioned as an art-infused community that celebrates Everett’s burgeoning public art scene. The design includes artwork on the building’s blank wall areas — both as a community-design feature and as a city design review condition. Skotdal’s other downtown projects have used similar themed-art approaches (aerospace at Aero, literary motifs at Library Place, theater design at Marquee across from the Village Theatre).

  • Everett-Delta Transmission Line: PUD Just Held Open Houses for a 3.5-Mile 115-kV Line That Connects to the Waterfront Corridor

    Everett-Delta Transmission Line: PUD Just Held Open Houses for a 3.5-Mile 115-kV Line That Connects to the Waterfront Corridor

    What is the Everett-Delta transmission line? Snohomish County PUD’s planned 3.5-mile 115-kV line that connects the Everett Substation (west of I-5 between McDougall and Smith) to the Delta Switching Station (just north of the SR 529 / West Marine View Drive interchange in north Everett). PUD hosted two public open houses on May 7, 2026 at PUD headquarters at 2320 California Street. The line is engineered to support growing electrical demand in and around Everett and prevent low-voltage conditions if local power is interrupted. Construction is targeted to begin in spring 2027, with the line in service by summer 2027.

    If you live in Everett and you have been wondering why a public utility line on the north end has been getting more attention this spring, here is the short version: Snohomish County PUD is building the infrastructure backbone that the waterfront, downtown, and north-Everett construction wave actually rides on.

    We stopped by the PUD open house messaging on May 7 — two sessions, 4 to 5:30 p.m. and 6 to 7:30 p.m., both at PUD headquarters at 2320 California Street in Everett — and what is striking is how directly this line maps to the development corridor we have been covering for months. The new Everett-Delta 115-kV transmission line connects two existing PUD assets that bracket the heart of the city: the Everett Substation, sitting just west of Interstate 5 between McDougall Avenue and Smith Avenue and north of 36th Street, and the Delta Switching Station, sitting just north of the State Route 529 / West Marine View Drive interchange in north Everett. That is the same West Marine View Drive corridor where the $113 million pipeline project, the Edgewater Bridge, and the Port of Everett’s terminal investments are all stacking up.

    Why this line is being built now

    PUD’s case for the new line is direct: increasing electrical demand in and around the city of Everett, and the need to keep voltage stable if local power is interrupted. That language is unsexy, but the substance is enormous. Everett is in the middle of a once-in-a-generation building wave — the Millwright District Phase 2’s 300-plus apartments, the Sage Investment Group conversion of the 9602 19th Street SE Econo Lodge to 124 studios, the Riverfront’s Eclipse Mill Park buildout, the downtown stadium with September 2026 groundbreaking ahead of it, and Skotdal Real Estate’s seven-story 102-unit Mosaic Apartments going up on Pacific Avenue. Every one of those projects pulls more load off the grid.

    A 115-kV line is the kind of mid-tier transmission that connects the bigger backbone to local substations. It is not a transmission “highway” in the BPA-scale sense, but it is the layer that determines whether neighborhoods can plug in the heat pumps, EV chargers, induction ranges, and apartment-tower elevator loads that follow new construction. Without it, fast-growing cities can hit a wall where the substation is fine, but the lines connecting substations cannot handle the swing.

    PUD’s stated benefit list pairs load growth with reliability — and in a city that has been adding new construction along West Marine View Drive at an unusual rate, the reliability part matters as much as the headroom. If local generation is interrupted, the new line gives operators a way to keep voltage from sagging at the Delta Switching Station — which feeds the north-Everett waterfront corridor directly.

    What the line will actually look like

    The new transmission structures will be similar in design and height to PUD’s existing 115-kV poles already in Everett — ductile iron and/or steel poles, similar profile to what is already in the corridor. PUD has stated that in the summer of 2025 it solicited community input on aesthetic enhancements, and the project page indicates that input will continue to inform the final route execution.

    The total length is approximately 3.5 miles, which puts this project on the smaller end of PUD’s current 2026 transmission projects (the Crosswind 115-kV line in Arlington, by comparison, is a different geography and ties into the new Crosswind Substation at the PUD’s North County Campus in Smokey Point). But the Everett-Delta line is the one that lands inside the city limits we cover.

    Timing — and why it matters for the waterfront

    PUD’s timing language is specific. With a route now chosen, the project moves to detailed engineering, permitting, right-of-way acquisition, and construction. PUD estimates the line will be in service by summer 2027.

    That is the same 2026-2027 window when the West Marine View Drive pipeline goes underground (the $113M combined sewer + 48-inch water main project the city approved on April 2), when Bayley Construction’s stadium site survey turns into vertical concrete in September 2026, and when Millwright District Phase 2 starts moving from site work into building shells. PUD building the transmission headroom in the same window means the grid is being prepped for the load that is about to land — not after.

    For the city’s part, the construction-window pause for the FIFA World Cup this summer (no in-road construction June through September in 2026 or 2027) keeps the corridor visible for waterfront events. PUD’s spring 2027 construction start sidesteps that political minefield by design.

    How this fits with everything else under construction

    If you have been reading the Waterfront & Development desk regularly, the names should be stacking up: the Lenora Regional Stormwater Treatment Facility (an $8.7M state-grant-funded plant breaking ground at S 1st & Lenora in Lowell this spring); the Port Gardner Storage Facility (a $200M+ combined sewer overflow project the state Department of Ecology ordered Everett to build); Port of Everett’s Segment E bulkhead final phase ($6.75M, 165 linear feet of wood-to-steel pile rebuild on West Marine View Drive); the federal $11.25M PIDP grant for Pier 3 structural rebuild; and the West Marine View Drive pipeline approved April 2.

    The Everett-Delta transmission line is the electrical leg of that same infrastructure stool. None of the apartments going up at Waterfront Place, the Mosaic, or Millwright Phase 2 generate their own power. They draw it from a system that has to grow in lockstep with the density.

    If you missed the May 7 open houses, the project page is still active and the PUD outreach team is still soliciting feedback on construction-impact mitigation. The full route map and FAQ live on PUD’s system improvements page.

    What we are watching next

    Three things on this line worth tracking through the rest of 2026:

    1. Right-of-way acquisition — PUD has chosen a route, but the easement and parcel-by-parcel acquisition work is where transmission projects get slow. Any contested takings will land on the Snohomish County PUD Commission’s monthly agenda. The commission meets at PUD HQ and the meeting cadence is on the snopud.com calendar.

    2. Permitting timeline — SEPA review and any City of Everett right-of-way permits required will be visible in the city’s permitting portal. A 3.5-mile transmission alignment through an urbanizing corridor typically generates a stack of structural and traffic-control permits even before vertical work starts.

    3. Coordination with the West Marine View Drive pipeline — Two major linear infrastructure projects in the same general corridor in the same window need to coordinate trench windows, utility crossings, and traffic control. The Everett Public Works team has run that gauntlet before (most recently on the Edgewater Bridge crossing of I-5), but the load is real.

    For now, the headline is simple. The grid is getting reinforced exactly where the city is getting denser. Everett’s transformation is being engineered, one transmission pole and one 48-inch pipe at a time.

    Frequently Asked Questions

    When will the Everett-Delta transmission line be in service? Snohomish County PUD estimates the line will be in service by summer 2027. Construction is scheduled to begin in spring 2027 and take approximately six months, following completion of detailed engineering, permitting, and right-of-way acquisition through 2026.

    How long is the Everett-Delta 115-kV transmission line? The line is approximately 3.5 miles long. It connects the existing Everett Substation, located west of I-5 between McDougall and Smith Avenues north of 36th Street, to the Delta Switching Station, located just north of the SR 529 / West Marine View Drive interchange in north Everett.

    Why does Snohomish County PUD need this new transmission line? Two reasons: to support increasing electrical demand in and around the city of Everett, and to maintain voltage stability and reliability if local power is interrupted. The line creates additional system capacity to serve the waterfront, downtown, and north-Everett construction wave.

    Where were the Everett-Delta open houses held? Both open houses were held on May 7, 2026 at Snohomish County PUD headquarters, 2320 California Street, Everett, WA 98201. Sessions ran 4 to 5:30 p.m. and 6 to 7:30 p.m., with identical content at each.

    What will the new transmission poles look like? The new transmission line and structures will be similar in design and height to the PUD’s existing 115-kV structures already in Everett, using ductile iron and/or steel poles. PUD solicited community input on aesthetic enhancements in summer 2025.

    How does this transmission line connect to Everett’s waterfront development? The Delta Switching Station endpoint sits just north of the SR 529 / West Marine View Drive interchange — the same corridor where Everett is investing in the $113 million pipeline project, the Edgewater Bridge, Port of Everett terminal infrastructure, and the Eclipse Mill Park / Shelter Holdings riverfront buildout. The new line adds transmission headroom to serve growing loads from new apartment construction, EV charging, and electrified buildings along that corridor.

    Where can residents track project progress and provide input? The project page lives on Snohomish County PUD’s system improvements website at snopud.com, and PUD Commission meetings are open to the public at the PUD HQ at 2320 California Street.

    📡 Exploring Everett Deep Coverage — Everett-Delta Transmission Line

  • What Restoration Companies Actually Sell For in 2026 (And What Kills the Deal at Close)

    What Restoration Companies Actually Sell For in 2026 (And What Kills the Deal at Close)

    Every restoration owner over fifty has the same question stuck in the back of their head: what is this thing actually worth? The honest answer in 2026 is somewhere between 2.3x SDE and 7x EBITDA — and the spread between those two numbers is not luck. It is the difference between a company a buyer wants and a company a buyer tolerates.

    Here is what is happening in the market right now, what private equity is paying, and what kills the deal at the eleventh hour.

    The 2026 Multiple Spread

    Restoration M&A in 2026 sorts cleanly into three tiers. The cutoffs matter — they are not aesthetic.

    Tier 1 — Sub-$2M revenue shops. Owner-operator businesses with one or two trucks, dependent on the founder for sales and crew leadership. These transact on Seller’s Discretionary Earnings (SDE), not EBITDA. Typical multiples: 2.3x to 3.0x SDE. The buyer is usually another restoration owner, a search-fund operator, or an industry veteran on their second act. There is no PE in this tier. The owner doing the work IS the asset, and that is exactly the problem.

    Tier 2 — $2M to $5M revenue shops. The PE feeder zone. These get bought by platforms like BluSky, First Onsite, Belfor, ATI, and Code Red as bolt-on acquisitions. Multiples: 3.0x to 3.5x SDE, or 4x to 5x EBITDA if the company is clean enough to have real EBITDA at all. Purchase prices land between $900K and $2.5M. This is the sweet spot for industry roll-ups — large enough to have a real second-in-command, small enough to absorb without indigestion.

    Tier 3 — $10M+ revenue, $2M+ EBITDA platforms. Now you are talking to PE directly, not through a strategic. Multiples: 5x to 7x EBITDA, occasionally higher for the right footprint. BluSky has announced 13 acquisitions in the last six years under Kohlberg & Company and Partners Group ownership. American Restoration rolled up 8 brands before exiting to Morgan Stanley. HighGround did 13 deals in five years before selling to Knox Lane. The playbook is well-documented. PE has put more than $6 billion into the space since 2018.

    What Buyers Actually Pay For

    The multiple is a function of risk, not affection. Sophisticated buyers pay up for five things, in roughly this order:

    1. Insurance carrier preferred-vendor status. If you are on the panel for State Farm, Allstate, USAA, Liberty Mutual, or any TPA program — Contractor Connection, Alacrity, Code Blue — that contract is the asset. It is also the hardest thing to replicate. Buyers will pay a premium for it because they cannot buy it any other way except by buying you.

    2. Mitigation-heavy revenue mix. Water mitigation runs gross margins around 70-80%. Reconstruction often runs 10% or less. A company that is 65% mitigation and 35% reconstruction is worth materially more than the same revenue split inverted. Buyers will pull your job-cost reports line by line during diligence to confirm the mix is real and not just how you are categorizing.

    3. Management depth below the founder. If you can take a two-week vacation and revenue does not blink, your multiple goes up by half a turn. If the phones stop ringing the moment you leave, you are selling a job, not a business. Hire a real general manager 18 months before you list.

    4. CAT exposure under 20%. Catastrophic event revenue is lumpy and cannot be modeled. If 40% of your last three years came from one hurricane season, buyers will discount that revenue heavily — sometimes valuing CAT-driven dollars at half the multiple of recurring carrier work. Diversify your revenue base before going to market.

    5. Clean books with a Quality of Earnings opinion. Every PE-backed deal includes a QoE — an outside accounting firm that re-audits your trailing twelve months and normalizes EBITDA. If your books are run on a personal-finance app and your CPA does taxes once a year, expect the QoE to find $200K-$500K of EBITDA adjustments that go against you. Spend $40K on a CFO-for-hire and a real GAAP P&L two years before sale.

    What Kills the Deal

    Roughly 30-40% of restoration LOIs do not close. Almost always for reasons the seller could have prevented.

    The biggest deal-killer is customer concentration. If one TPA program represents more than 35% of revenue, buyers panic. They have seen what happens when Contractor Connection decides to rebid a region — entire $8M revenue lines disappear in a quarter. Diversify before you list.

    The second is uncollected aged receivables. Restoration AR over 90 days is not an asset, it is a write-down waiting to happen. Buyers will deduct uncollected AR from purchase price dollar-for-dollar. Aggressively collect or write off everything before you go to market.

    The third is licensing and certification gaps. IICRC, state contractor licenses, mold remediation certifications by state — buyers run a full compliance audit. A single expired contractor license in a key state can cost $50K-$150K at close.

    The fourth is founder dependency on first-call relationships. If the property manager calls you personally when there is a flood — not a dispatch number, not a sales rep — buyers will require an earnout structure that makes you stay another three to five years. Most owners hate earnouts because they convert sale price into deferred contingent comp. Build the dispatch infrastructure before you list, and you keep the cash up front.

    The Honest Bottom Line

    If you are a $3M revenue restoration company today and you want a clean exit at a real multiple, you have an 18-to-24 month preparation window. Use it to get the books on accrual, hire a GM, diversify off any single TPA, build mitigation revenue past 60% of mix, and get every certification current.

    Do that, and a $3M shop running 18% EBITDA margins ($540K) sells at 4.5x to a strategic — about $2.4M cash at close. Skip it, and the same company sells at 2.6x SDE — closer to $1.4M, often with a punishing earnout attached.

    The difference is one million dollars. The work to capture it is roughly nine months of operator focus. That is the highest-ROI work an exiting restoration owner can do.

  • Mason County Roads — May 10, 2026

    May 10, 2026 — Sunday morning brief. Sources checked: WSDOT Olympic Region highway alerts, Mason County Public Works, MasonWebTV road work feed, Shelton-Mason County Journal. Live conditions: WSDOT highway alerts · WSDOT travel map.

    Active Alerts

    No active alerts from WSDOT or Mason County Public Works this morning. Mason County highways — SR-3, US-101, SR-106, SR-302, SR-108, and SR-119 — are open and operating under normal Sunday conditions. No emergency closures or unscheduled lane restrictions reported overnight.

    Major Projects — Current Status

    ProjectStatusEst. CompletionSource
    SR-3 Freight Corridor (Belfair Bypass)Construction 2026, completion 2028 — funding at risk. Supplemental budget includes $48.3M in 2025–27 biennium; Ferguson budget proposes delaying final phase from 2027–29 to 2031–33 biennium.2028 (if funded)Shelton Journal 2/26/26
    Olympic Highway North (Shelton)Design phase — bid spring 2027, construction summer 20272027–28Shelton Journal 3/19/26
    SR-3 Shelton Safety (Craig Rd to Arcadia Rd)Pre-design — roundabouts planned, no construction dateTBDWSDOT engage
    SR-3 Belfair Widening (MP 25.3–27)Active constructionOngoingWSDOT

    Commuter Notes for Today

    • SR-3 Belfair (MP 25.3–27): Belfair widening construction zone remains active. Travel time normal on Sunday — no flagging or daytime lane closures reported. Use caution through the work zone.
    • US-101 Shelton / Kamilche: No reported alerts. Sunday volumes light. Drive normally between Olympia, Shelton, and Hoodsport.
    • SR-106 along Hood Canal (Union area): Open. No alerts overnight on the Hood Canal corridor.
    • SR-302 (Key Peninsula side toward Victor): Open. The SR-302 Victor Creek fish-barrier project completed major construction in December 2025 — the new bridge is carrying traffic and lane configurations are back to normal.

    Report a Road Issue

    • State highways (SR-3, US-101, SR-106, SR-302, SR-108, SR-119): Call WSDOT at 511 or visit WSDOT highway alerts.
    • Mason County roads: Mason County Public Works at (360) 427-9670 or report online at masoncountywa.gov.
    • City of Shelton streets: Shelton Public Works at (360) 432-5100.

    This brief is compiled each morning from public sources. For real-time conditions, always check the WSDOT live travel map before you drive. Conditions can change quickly — especially on SR-3 and US-101 where flagging operations and weather-related restrictions can appear with little notice.

  • The HUB Turns 25: Belfair’s Home Base for Seniors Keeps Getting Busier

    The HUB Turns 25: Belfair’s Home Base for Seniors Keeps Getting Busier

    There is a building on Old Belfair Highway that most of us have driven past a hundred times — tucked just off Highway 3, easy to miss if you’re rushing toward the Belfair Town Center. But if you stop and walk in on a Monday or Tuesday morning between 10 and noon, you’ll find live music already playing and a salad bar set up on a pay-what-you-can basis. That’s The HUB, and it has been the unofficial living room of North Mason County for 25 years.

    The organization was founded in 2001 as a 501(c)(3) under a simple mission: support independent living for our senior and disabled neighbors. For the first 15 years, The HUB operated as a mobile, volunteer-driven service network — rides to appointments, help with errands, a free medical lending library, and a food commodities program for seniors. All of it run by neighbors helping neighbors.

    In 2016, the dream got a building. Les and Betty Krueger offered matching funds to help purchase land on Old Belfair Highway, and our community rallied to raise the rest, funding the first phase of a purpose-built senior center. The name is an acronym — Hospitality, Unity, and Belonging — but it has also just become the plain-English word for what happens there. The HUB is where people gather.

    Today, the center at 111 NE Old Belfair Hwy runs a packed calendar any given week. Monday and Tuesday mornings bring free live music open to the whole community — not just seniors. Family BINGO lands on the first Friday of every month. Fitness classes, painting, writing workshops, cooking classes, and health events fill out the rest. The Great Room and commercial kitchen are available for community rentals and private fundraisers.

    The HUB Shop — or as the staff calls it, Sales Helping Other People — operates its own full schedule: Monday through Saturday, 9:30 a.m. to 5:30 p.m. It’s a thrift store where proceeds cycle back into HUB programs. Generations of Belfair families have donated furniture, clothes, and household goods here, and picked up unexpected finds in return.

    The Neighbors Helping Neighbors program remains the quiet backbone of the whole operation. It’s not glamorous: rides to doctors, help with grocery runs, a borrowed wheelchair or walker when you need one. But it is how The HUB’s original 2001 mission still shows up in real, daily form for people who would otherwise navigate North Mason without much support.

    If you have never been inside — or if it’s been a while — the center is open Monday through Thursday, 10 a.m. to 4 p.m. The phone is (360) 275-0535. Find The HUB at 111 NE Old Belfair Hwy, on the left-hand side of Old Belfair Highway coming from downtown Belfair, just past where the road bends away from Highway 3.

    Related Coverage from Belfair Bugle

  • 5 GEO and AEO Case Studies From 2026 — What Actually Worked, Decoded

    5 GEO and AEO Case Studies From 2026 — What Actually Worked, Decoded

    Most GEO and AEO case studies you can find online are vendor-published and short on implementation detail. So instead of stacking another “look at this 300% lift” headline, this piece walks through five publicly documented results from 2026 — and pulls out the structural change that actually drove the win in each one. If you want to copy what works, copy the structure, not the percentage.

    1) HubSpot: 3x lead conversion from AEO traffic

    HubSpot’s own 2026 State of Marketing reporting found 58% of marketers saying AI-referred visitors convert at higher rates than traditional organic, with HubSpot itself reporting roughly 3x better lead conversion from AEO sources versus other channels. The implementation pattern across HubSpot’s blog: question-led H2s, a 40–60 word direct answer in the first paragraph below the heading, then expanded context, then a structured FAQ block with FAQPage schema.

    The before/after isn’t “more content.” It’s “the same content, restructured so the answer arrives in the first 60 words.” That single edit is what featured snippets and AI Overviews both reward.

    2) Hashmeta e-commerce client: +50% zero-click visibility

    Hashmeta documented a 50% increase in zero-click visibility for an e-commerce client after a targeted AEO sprint. The lever: rebuilding product and category pages around explicit question intent (“what is the difference between X and Y,” “is X worth it for Z use case”) and adding HowTo and FAQPage schema. The page didn’t get more traffic from the same query — it started winning the answer position on related queries it wasn’t competing for before.

    The takeaway for practitioners: zero-click visibility is its own funnel. Track it separately from sessions, because the value shows up in branded search lift two to four weeks later, not in same-day clicks.

    3) SaaS brand: 20+ free-trial signups per month from ChatGPT citations

    One SaaS case study circulating in the GEO community in early 2026 reported 20+ free-trial signups per month attributed directly to ChatGPT citations, identified via a unique UTM and a referral-source filter in their analytics. The structural pattern: a single canonical comparison page per top competitor, written as a third-person reference rather than first-person marketing, with a clear definition block, a structured comparison table, and a “when to choose X” section.

    This is the format ChatGPT cites because it’s the format ChatGPT was trained to produce. Match the output shape and you become the source.

    4) Generic brand study: 140% lift in AI-driven search traffic

    A widely cited 2026 GEO case study reported a 140% increase in LLM and AI-driven search traffic alongside a 62% rise in AI mentions after a strategy that prioritized entity saturation, internal-link clustering, and structured data over keyword density. The implementation detail worth copying: a single hub page per entity with at least 15 distinct factual data points, then 8–12 supporting articles linking back to it with descriptive anchor text.

    The 15-data-point threshold matches what GEO researchers have flagged repeatedly: articles with 15+ verifiable data points receive substantially more AI citations than articles with fewer than five.

    5) Mangools: featured-snippet capture from a single edit

    Mangools published a walkthrough showing how rewriting one blog post to lead with a 50-word direct answer captured a featured snippet for a head-term query, with the resulting traffic and brand exposure outpacing the rest of the content cluster. No new backlinks, no new content — just a structural rewrite of the first 100 words.

    The pattern across all five

    Every win has the same shape: question-led H2, 40–60 word direct answer, structured supporting content, schema markup. Here is the minimum viable AEO block, drop-in ready:

    <h2>What is generative engine optimization?</h2>
<p><strong>Generative engine optimization (GEO) is the practice of structuring web content so AI systems like ChatGPT, Claude, Gemini, and Perplexity cite it as a source.</strong> Unlike SEO, which optimizes for ranking in a list of links, GEO optimizes for being included in a generated answer. The core levers are entity clarity, factual density, structured data, and crawlability via LLMs.txt and robots.txt.</p>

<script type="application/ld+json">
{
  "@context": "https://schema.org",
  "@type": "FAQPage",
  "mainEntity": [{
    "@type": "Question",
    "name": "What is generative engine optimization?",
    "acceptedAnswer": {
      "@type": "Answer",
      "text": "Generative engine optimization (GEO) is the practice of structuring web content so AI systems cite it as a source in generated answers."
    }
  }]
}
</script>

    The measurement layer

    None of these case studies mean anything without isolation. The minimum tracking stack: a referrer filter for chatgpt.com, perplexity.ai, claude.ai, gemini.google.com, and copilot.microsoft.com in GA4; a separate event for zero-click impressions from Google Search Console; and a manual citation log — query a representative model with your top 25 prompts weekly and record whether your domain is cited. The third one is what most teams skip, and it’s the only one that tells you whether GEO is working before traffic shows up.

    What to copy this week

    Pick your top five highest-intent pages. For each one, rewrite the first 100 words as a direct-answer block, add a single FAQPage schema with three questions, and add the page to your LLMs.txt manifest. That is the entire implementation. Every case study above is a variation on those three moves.

  • Mason County Community Spotlight: Sound Learning and Kitten Rescue of Mason County — May 2026

    Mason County Community Spotlight: Sound Learning and Kitten Rescue of Mason County — May 2026

    When you think about what holds a community together, the answer often shows up quietly: in a Shelton classroom where adults study for their GEDs at night, or in a shelter along State Route 3 where volunteers coax a feral kitten toward trust. This week’s Community Spotlight shines on two Mason County nonprofits — Sound Learning and Kitten Rescue of Mason County — that have been doing exactly this kind of unglamorous, essential work for decades.

    Sound Learning: 35 Years of Second Chances in Downtown Shelton

    Sound Learning, located at 133 W. Railroad Ave. in downtown Shelton, has been opening doors for adult learners in Mason and Thurston Counties since 1991, when it was founded as Mason County Literacy. At its 20th anniversary, the organization adopted a new name to reflect its expanded mission: building the skills workers, parents, and families need to navigate the 21st century. Now in its 35th year, Sound Learning remains one of the most consequential — and least visible — institutions in Mason County.

    The organization offers several tracks: Adult Basic Education including High School+ and GED preparation, English Language Acquisition at six levels, and an Open Doors program that serves immigrant youth ages 16 to 21 in partnership with the Shelton School District. Students receive small-group instruction supplemented by distance learning, and classes are scheduled to fit around the demands of work and family. That accessibility is a deliberate design choice: the people Sound Learning serves are often working multiple jobs or raising children while pursuing a diploma that the rest of society already takes for granted.

    This spring, Sound Learning received a significant vote of confidence in the form of a three-year, $150,000 grant from The Harvest Foundation. The funds will be used to expand educational programs, update essential technology including computers for digital literacy instruction, and invest in staff development to keep instructors current with best practices.

    “We are incredibly grateful to The Harvest Foundation for their generous support,” said Ava Taylor-Sisk, Sound Learning’s interim director. “This funding will allow us to better serve adults in our community who are working hard to build brighter futures for themselves and their families. Investments in education strengthen our entire region.”

    The organization’s board of directors draws from across the county’s institutional fabric: Chairman Billy Thomas is marketing director at Peninsula Credit Union; board member Jeff Slakey is a journalist and media coordinator at KMAS; and Vice-Chairman Penny Wilson serves as director of the Mason County Senior Activities Center. That connectivity keeps Sound Learning embedded in the networks residents depend on.

    The community has an opportunity to celebrate Sound Learning in person this coming Saturday. The 30th Annual Spell-E-Bration fundraiser takes place Saturday, May 16, 2026, from 4 to 8 p.m. at the Mason County Senior Activities Center — The Pavilion at Sentry Park, 190 W. Sentry Drive, Shelton. The evening features a spelling competition where community teams compete for the Top Spelling Champs Award, a silent auction, a Beehive Bonanza prize drawing, and a dessert and appetizer bar. Sponsorships and donations are still being accepted at soundlearning.co.

    Sound Learning can be reached at (360) 426-9733 or staff@soundlearning.co. The learning center is located at 133 W. Railroad Ave., Shelton.

    Kitten Rescue of Mason County: 26 Years as the County’s Only Cat Shelter

    In 1999, there was nowhere in Mason County for an abandoned cat or kitten to go. A small group of local volunteers decided that was unacceptable, and Kitten Rescue of Mason County was born. Twenty-six years later, KRMC remains the only physical shelter in Mason County devoted exclusively to cats and kittens — and it still operates as a no-kill facility.

    Located at 420 SE State Route 3 in Shelton, the shelter has grown from its grassroots origins into a facility with a main cottage and six small outbuildings, two of which were added in 2021 to meet growing demand. Beyond the walls of the shelter, a network of foster families helps socialize kittens before adoption, preparing them for the homes they’ll eventually join. The organization also runs a free feral “Fix and Release” program and provides low-income spay and neuter assistance — addressing the root causes of cat overpopulation throughout Mason County rather than simply managing its symptoms.

    KRMC is 100% donor-supported. Its primary fundraising engine is a regular garage sale held at the 420 SE State Route 3 location, where 100% of proceeds go directly to operations: food, medical care, spay and neuter services, and shelter. The organization held a garage sale yesterday, Saturday, May 9. Residents interested in donating items for future sales should note that the next donation window opens May 16. Accepted items must be complete, clean, and gently used — the shelter cannot accept computers, televisions, mattresses, large furniture, or damaged goods, as dump fees would directly reduce care for the animals.

    KRMC noted on its website that it is currently at capacity and cannot accept additional cats or kittens at this time. Residents who have found a stray or need assistance are encouraged to check the additional resources page at kittenresq.net for referrals to other organizations that may be able to help.

    For those looking to contribute, Kitten Rescue accepts donations at kittenresq.net, relies on volunteers for daily care, socialization, fostering, and behind-the-scenes administration, and can be reached at 360-427-3167 or krmasoncounty@gmail.com.

    Why These Stories Matter

    Together, Sound Learning and Kitten Rescue of Mason County represent something Mason County does quietly well: building institutions that meet real needs, run by neighbors who show up year after year because no one else will. If you’ve benefited from either organization, or know someone who has, this is a good week to say thank you — or to chip in.

  • Shorebirds and Halibut: A Perfect Sunday on Grays Harbor

    Shorebirds and Halibut: A Perfect Sunday on Grays Harbor

    The South Coast of Washington doesn’t wait for you to plan ahead. This week, the window is wide open on two experiences you’d drive hours for — and both happen to be peaking right now. The Grays Harbor National Wildlife Refuge in Hoquiam is in the final days of one of the Pacific Coast’s most extraordinary wildlife events, while out at the Westport docks, halibut season is running on Sundays all month. Whether you’re a birder, an angler, or just someone who needs a genuinely good Sunday, the South Coast is delivering.

    The Last Days of Spring Migration at Bowerman Basin

    Every spring, hundreds of thousands of shorebirds descend on the Grays Harbor Estuary during their northbound migration from South America and Central America toward breeding grounds in Alaska and the Arctic. The Grays Harbor National Wildlife Refuge — specifically the tidal flat ecosystem known as Bowerman Basin — sits at the center of this spectacle. The U.S. Fish & Wildlife Service describes Grays Harbor as one of the largest concentrations of shorebirds on the west coast, south of Alaska, and the numbers bear that out: in peak years, the flats host birds so numerous they seem to shift like a living tide.

    The migration window runs from late April through mid-May, and May 10 sits squarely in it. The dominant species right now include Western sandpipers and dunlins — which together account for roughly 80 percent of the birds present — along with short-billed and long-billed dowitchers, black-bellied plovers, red knots, and semipalmated plovers. These birds are fueling up on the estuary’s rich mudflat invertebrates before pushing north. The urgency of their schedule means they’re concentrated, active, and visible in extraordinary numbers.

    The Sandpiper Trail is your access point: a wooden boardwalk loop that leads through salt marsh and alder-cottonwood forest out to open benches overlooking the intertidal flats. The trail is open sunrise to sunset year-round, and there is no entrance fee. Reaching the trailhead requires a short 1/3-mile walk from the parking area at 1000 Airport Way, Hoquiam — through a cooperative agreement between the U.S. Fish & Wildlife Service and the Port of Grays Harbor, which manages the adjacent airfield.

    The tide is everything here. Birding is best within three hours of high tide, when rising water pushes the shorebirds off the exposed flats and concentrates them near the boardwalk trail. Check the tide table at tides.net before you go, and aim to arrive about two hours before high water. There are no restrooms or potable water at the refuge, so come prepared. The payoff on a good tidal morning — a wall of sandpipers lifting and wheeling over the gray-green water — is one of those sights that recalibrates your sense of what the natural world can do. Reach the refuge at (360) 753-9467 through the Nisqually National Wildlife Refuge Complex.

    Westport Halibut: The Season Is Running Right Now

    Forty miles down the coast, Westport is operating in full halibut mode. The Washington Department of Fish and Wildlife opened Marine Area 2 — the Westport-Ocean Shores zone — to recreational halibut fishing on April 30, 2026, with designated open days running through May 31. This Sunday is one of them.

    The 2026 schedule for Marine Area 2 runs Tuesdays, Thursdays, Fridays, and Sundays through the end of May. The daily catch limit is one halibut, and the annual limit is six per angler. There is no minimum size restriction. All anglers are required to record their catch on a WDFW catch record card — now available as an electronic version through the WDFW’s MyWDFW and Fish Washington mobile apps.

    Westport holds the coast’s largest charter boat fleet, and most of the action happens far offshore around the edges of Grays Canyon, with depths reaching 600 feet or more. Charter trips typically depart well before dawn and return by early afternoon — make sure to confirm departure times when you book. Several Westport operators are actively booking halibut trips for remaining May open days, and availability on prime Sunday slots fills quickly. A solid starting point for the current charter fleet lineup is experiencewestport.com.

    One practical note: the season can close before May 31 if the quota for Marine Area 2 — set at 65,857 pounds for 2026 — is reached. Always confirm that the area is still open before heading to the dock by checking wdfw.wa.gov or the WDFW emergency fishing rules page. Quota tracking information is updated in-season.

    Plan Your Visit

    For Bowerman Basin: Drive to 1000 Airport Way, Hoquiam, WA 98550. Parking is free, the Sandpiper Trail is open sunrise to sunset, and there is no entrance fee. Time your visit to arrive within three hours of high tide for the best shorebird viewing. The migration window closes around mid-May — this weekend is the time to go. Contact the refuge through the Nisqually NWR Complex at (360) 753-9467, or visit fws.gov/refuge/grays-harbor.

    For Westport halibut: The remaining open Sundays in May are the 17th and 24th after today. Visit experiencewestport.com for the charter fleet directory, or contact operators directly to check availability. Bring or download a WDFW catch record card before boarding. For in-season closures or quota updates, visit wdfw.wa.gov. The drive from Hoquiam to Westport is approximately 25 minutes via US-12 and State Route 105 — putting both stops on the same day trip if you time the tides right.

  • Composting Is Not Cleaning

    There is a place in every working life where ideas that were once worth marking go to sit. They are not active. They are not dead. They are not being worked. They are also not being released.

    Most workspaces have one. The mature ones have many.

    The conventional name is backlog or drafts or inbox. None of those names tell the truth about what the pile actually is. The pile is a mausoleum of former selves. Each item there was flagged by a version of the operator who believed they would act on it. That version is gone. The item remains.

    The instinct is to call this a process problem. Better triage. Better tagging. Better deadlines. A weekly clearance ritual. The instinct is wrong, which is why the rituals never hold.

    The previous piece named this directly: composting living work is a grief problem, not a process problem. That was the first half of the move. This is the second.

    Three Layers of the Pile

    Items in the pile are in three layers, and they should be treated differently.

    The top layer is triage hygiene. Auto-captured noise, duplicates, half-finished references whose context is gone. Most operational advice ends here. This is the layer where checklists and review cadences earn their keep. It is also the layer that is rarely the real problem.

    The middle layer is the items that still feel possible. Each one has a small private case for itself. I could still do this. The operator returns to it monthly and finds the case unchanged — which is to say, the case is no longer being made by current evidence; it is being made by inertia and by the original belief that it was worth marking. Middle-layer items survive triage because triage asks the wrong question. Triage asks is this still useful? The honest question is am I still that person?

    The bottom layer is the dangerous one. These are the items whose continued presence in the pile is doing structural work for the operator’s self-image. They are not failures of execution. They are placeholders for an identity. As long as the item sits there, the operator is still legibly the kind of person who would write that essay, build that product, finish that draft. Removing the item is not an act of housekeeping. It is a small private retraction of a public claim — or a small public retraction of a private one.

    This is the layer the system cannot help with. No score, no priority field, no dashboard sees this layer because there is nothing operationally distinct about it. The signal is internal. The operator knows.

    The Forest Doesn’t Help Here

    The forest does not feel bad about the dead branch. The phrase is true and almost useless to a person standing in front of their compost pile holding an item with their name on it. Ecological metaphors describe an outcome whose emotional precondition is exactly what the operator does not have.

    Composting at organizational or personal scale requires the operator to do something the forest never has to do: contradict a former judgment. The forest’s branch did not announce itself when alive. It was just functional. The drafted essay announced itself — was caught, named, marked, given coordinates. It promised something. Composting is breaking that promise. The pile is silent only because no one is saying out loud what it would mean to retire each item: I am not who I thought I was when I added you.

    That is why the act is slow. That is why every tool that promises to make it fast eventually fails. The bottleneck was never throughput.

    Two Failure Modes

    There is a productive failure mode here, and a corrosive one.

    The productive failure: an operator who composts slowly because each act is being given the weight it deserves. The pile shrinks unevenly. Some items leave in batches. Some take a year. The shape of the descent is honest. The operator emerges with fewer items and a clearer sense of which versions of themselves they are still in negotiation with.

    The corrosive failure: an operator who refuses to compost at all and recodes the pile as backlog. The items are then re-examined, reprioritized, re-tagged, lightly edited. The grief is laundered as process. The pile does not shrink. The mausoleum is maintained but never visited. The operator stays legible to themselves as someone who will. The cost is not the items — the items were never going to ship. The cost is that an entire psychic load goes on accruing interest in a currency the operator did not agree to pay.

    A workspace full of unkilled drafts is not a productivity problem. It is a personality problem in workspace clothing.

    What Composting Well Actually Looks Like

    Not efficient. The first sign that an operator is doing this honestly is that the act has weight. They do it less often than the dashboard suggests. They do not batch-delete. They name what is being released — not in detail, not as eulogy, but with enough specificity that they cannot pretend later that it never happened.

    The released items go somewhere reviewable. Not to a hidden trash. To a list with dates. The point of the list is not to bring items back. The point is to make the act undeniable. An operator who can later open the list and read the names is an operator who can no longer claim those projects are pending.

    A small re-entry condition is allowed, borrowed from the discipline of principled refusal: a composted item is permitted to come back, but only under a different premise. If the case for re-entry is the same case that was made the first time, the answer is no — the case has already been heard.

    The Terms of the Deal

    The deeper point, which the previous piece pointed at and did not unfold:

    Compounding systems generate more captures than any operator can ever commit to. The capture-commitment gap is not a bug — it is the organizing fact of working at scale with intelligent infrastructure. The compost pile is the visible artifact of that gap. It is not a sign of failure. It is the sign that the system worked.

    An operator who refuses to grieve their compost pile is an operator who has not yet accepted the terms of the deal. They wanted leverage. The leverage came. Some of the leverage takes the form of not getting to do everything they once thought they would.

    This is where the architecture shows its temperament. A surfacing system that ranks captured items by recency or volume is happy to let the operator confuse the pile with a queue. A surfacing system honest about its own purpose has to admit that some of what it captures is not for committing — it is for releasing. The willingness to flag an item as candidate for compost is the system version of the operator’s grief. Most workspaces will not build it because it makes the surface look smaller. The ones that do are participating in the actual work.

    The forest does not feel bad about the dead branch. The operator does, and probably should — once. The discipline is letting the feeling do its work and then moving the branch to the pile, where the forest can finally start its own slow indifferent recycling.

    You will know the work is done when you can walk past the compost pile without checking it.

  • Claude Code for Teams: What to Commit, What to .gitignore, and What Actually Survives a Pull Request

    Claude Code for Teams: What to Commit, What to .gitignore, and What Actually Survives a Pull Request

    Last refreshed: May 15, 2026

    Most teams I see roll out Claude Code by handing every engineer the install command and walking away. Three weeks later, half the repo has personal preferences committed to .claude/settings.json, the other half has a CLAUDE.md that contradicts the actual review process, and someone’s customized subagent is silently making code changes nobody else on the team understands.

    There is a better way, and it lives in the split between three files: CLAUDE.md, .claude/settings.json, and .claude/settings.local.json. Get this split right, and Claude Code becomes a force multiplier for the team. Get it wrong, and you are shipping AI-generated code that nobody owns.

    The Three-File Split

    Here is the rule, no exceptions:

    CLAUDE.md — committed. Project root. Every engineer’s session reads this at startup. Put your architectural decisions, preferred libraries, naming conventions, and a review checklist here. If you would not write it on a whiteboard for a new hire, it does not belong here.

    .claude/settings.json — committed. Team-wide tool permissions, default models, and hooks. This is the file that keeps personal flagship-model enthusiasts from blowing through your team’s budget when claude-sonnet-4-6 would have done the job. If you let everyone default to claude-opus-4-7 for routine refactors, your monthly invoice will tell you about it.

    .claude/settings.local.json — gitignored. Personal preferences, individual MCP server configs, anything that varies by engineer. Add this line to your .gitignore on day one:

    .claude/settings.local.json

    If you do not, someone will commit credentials by Friday. Audit your existing repo right now: git log --all --full-history -- .claude/settings.local.json will surface any history that needs scrubbing.

    The mistake I see most often is teams committing settings.local.json because someone copied a tutorial that did not make the distinction clear. That copy-paste error is the single most common Claude Code rollout failure I have seen this year.

    Shared Subagents Are the Real Win

    Project subagents live in .claude/agents/ and they ship with the repo. This is where teams compound value. A subagent for security review, one for accessibility audits, one for SQL migration safety — defined once, used by every engineer, every PR.

    A subagent definition is a markdown file with YAML frontmatter and a system prompt. When you commit it, every teammate’s claude invocation can call it. The subagent inherits your CLAUDE.md context automatically, so you do not have to redefine the project’s coding standards inside each agent.

    Here is the trap: do not put twelve subagents in there on day one. Start with one. The team’s most painful repeated review task is the right candidate. Whatever takes a long time and pulls in multiple engineers per PR — that is your first subagent. After two weeks of using it, you will know whether the second one is worth defining.

    CLAUDE.md Is a Living Document, Not a Manifesto

    The longest CLAUDE.md files I see are the worst-performing. Engineers do not read 4,000-word context files, and neither does Claude in any useful way — at some point you are paying for tokens that just dilute the signal.

    The CLAUDE.md files that actually shape behavior are usually compact, structured around three things:

    1. What this codebase is and what it is not.
    2. The handful of rules that get a PR rejected — test coverage, naming, error handling, dependency policy.
    3. A pointer to where deeper documentation lives.

    If your CLAUDE.md has a “philosophy” section, delete it. If it has a “history of the project” section, delete it. The file is read every session — make every line earn its tokens.

    CI/CD: Run Claude Code on PRs, Not in Place of Reviewers

    The pattern that works in CI is automated triage, not automated approval. A GitHub Actions workflow that runs Claude Code on every PR to check for things humans miss — missing tests, secrets in logs, public APIs without docstrings — adds value. A workflow that approves and merges PRs adds liability.

    Anthropic’s official GitHub Actions integration handles the auth and runs Claude Code headlessly. The realistic use cases:

    • Comment on PRs with a structured review (not a merge gate).
    • Auto-label PRs based on the diff.
    • Flag suspected regressions before a human reviewer opens the PR.

    Avoid: anything that auto-merges, anything that posts directly to production-facing systems, anything that calls a paid API on every commit to a feature branch. The bill compounds quickly when CI fires Claude on every push to every developer branch. Gate the workflow on PR-target branches only, or on labels.

    Where Claude Code for Teams Loses Today

    The honest list:

    • No native role-based permissions inside a single repo. If you want a junior engineer’s Claude Code to be more restricted than a senior’s, you have to enforce it through settings.json and trust everyone to not edit it. The Enterprise plan adds SSO, SCIM, and audit logs at the workspace level, but inside the repo, Claude Code itself does not differentiate by role.
    • No first-class secret scanning before commits. Hooks can plug this gap, but you have to wire pre-commit yourself.
    • Shared MCP servers are still per-developer auth. A team-shared Linear or Jira MCP, for example, still requires each engineer to authenticate individually.

    The Team plan addresses workspace-level governance through Premium seats, which is the tier that actually unlocks Claude Code for teammates. The Enterprise plan layers on SSO, SCIM, and audit logs. Neither makes the in-repo configuration questions go away — those are still your team’s problem to solve.

    Model Selection Is a Team Decision

    This one matters more than people realize. Default everyone in .claude/settings.json to claude-sonnet-4-6 for day-to-day work, with claude-opus-4-7 available for explicitly hard tasks. The current Anthropic lineup as of this writing — flagship claude-opus-4-7, workhorse claude-sonnet-4-6, fast claude-haiku-4-5-20251001 — is documented at docs.anthropic.com/en/docs/about-claude/models, and the model strings change frequently enough that hard-coding them in scripts has bitten me twice this year. Read that page, do not memorize it.

    A team that defaults to flagship for everything and a team that defaults to workhorse with selective escalation will see meaningfully different invoices for substantially the same productivity. Make the choice consciously.

    The 20-Minute Setup

    If you are rolling Claude Code out to a team next week:

    1. Add .claude/settings.local.json to .gitignore. First commit, today.
    2. Write a focused CLAUDE.md covering review-blocking rules. Ship it short.
    3. Create one subagent in .claude/agents/ for the team’s most painful review task.
    4. Add a single GitHub Actions workflow that runs Claude Code on PRs in comment-only mode.
    5. Schedule a 30-minute team review of the CLAUDE.md every two weeks. Delete more than you add.

    That is it. Everything else is iteration. The teams that succeed with Claude Code treat the configuration as code — versioned, reviewed, and pruned. The teams that fail treat it as a personal productivity tool that happens to be in a shared repo.

    Decide which kind of team you want to be before the third engineer commits.