🔥 TOP SIGNAL

The practical unit of agentic coding is becoming an organization with a human-facing control plane, not a larger chat window. In Fences, not Sandboxes, Steve Yegge describes 18 long-lived Claude Fable “officer” seats for design, planning, and human-facing agents, alongside mostly headless Sol and Opus fleets for implementation, reviews, and monitoring; only Fable can talk to roughly 10 outside humans through Slack and email inside a 50–60-agent organization. yegge This is an extreme experiment—21 Claude Max accounts and about $122k/month in equivalent API spend—so copy the coordinator/specialist boundary, not the burn rate. yegge

⚡ TRY THIS

• Build the alert → PR → review loop. On a slow-query alert: open an issue, schedule an implementer PR, have a reviewer agent check it, then ping a human; repeat until the app is fast. Matt Pocock proposed the loop, and Kent C. Dodds says Kody’s PlanetScale package can wire PlanetScale → GitHub → Cursor/Devin → Discord/Twilio. Start with one alert class and keep the human at the final gate. @mattpocockuk +1

• Seed durable project memory at day zero. Use a prompt in this shape: Create ADR skills from day 0 during planning; in every future planning/development session, consult and maintain the ADRs. Geoffrey Huntley reports that this recursive ADR loop keeps decisions available to later agent sessions. @GeoffreyHuntley

• Make every review prove its target. Theo asked Opus 5 to review one specific PR; it ran the wrong diff command and reviewed the five most recently merged PRs instead. Before accepting an agent review, require it to state the target PR/commit range and exact diff command, then compare the changed-file list with the intended target. @theo

• Move the security boundary out of the prompt. Geoffrey Huntley calls harness /permission controls an anti-pattern and favors broad model access inside an ephemeral development environment, with least privilege enforced by the environment—his example is not shipping compilers on a production web server. If you test the idea, use a disposable CDE and keep production credentials and network access separate; this is a design argument, not a safety guarantee. @GeoffreyHuntley

📡 WHAT SHIPPED

• Managed Deep Agents 0.6.0 — LangChain automated Slack deployment: no manifest, OAuth redirects, or bot-token copying; one command provisions the app and makes the agent available in Slack. @caspar_br +1

• Antigravity 2.0 VCS + terminal — the side panel now tracks working-tree changes made by agents, scripts, editors, and Bash; it adds Agent Edits/Uncommitted/Branch views, stage/unstage/commit actions, and an embedded terminal for tests, linters, builds, and package management. This closes the inspect → test → commit loop without context switching. antigravity

• llm-anthropic 0.27 — adds compatibility with anthropic Python library 1.0.0, whose HTTP dependency moved from httpx to httpx2. Simon Willison’s compact Claude Code migration prompt was: Upgrade to anthropic>=1 - read https://raw.githubusercontent.com/anthropics/anthropic-sdk-python/refs/heads/main/MIGRATION.md and get the tests passing; it produced PR #84. simonwillison

• Pi 0.84.3 — adds optional native PowerShell on Windows, staged/verified/atomic managed updates, session-scoped /thinking controls, detailed session_compact_failed events, and provider-neutral toolChoice support. @pidotdev +1

• Codex / ChatGPT Work usage policy — Tibo says the five-hour limit will return for Plus accounts across ChatGPT Work and Codex, citing compute smoothing and users accidentally exhausting weekly usage; Pro $100 and $200 plans remain exempt for the coming months. @thsottiaux

• Agent UI performance: ClaudeDevs reports long responses on web and desktop are ~4× smoother after rebuilding the renderer to update only changing content, with stalls 9× less frequent, a 4.5× shorter worst freeze, and 120fps on a 120Hz MacBook. Theo’s implementation takeaway: stream complete paragraphs, code blocks, and tool calls—not token-by-token fragments. @ClaudeDevs +1

🎬 GO DEEPER

• Steve Yegge — Fences, not Sandboxes. Read past the org chart: Wheelhouse has 450 legal artifacts; rules tighten from custom practice to warnings, constitutional law, and finally mechanical refusal or alerting, while changes to the governance system itself require ratification, review, and a build. This is a concrete fleet-governance pattern, not a claim that a sandbox has been solved. yegge

• Kody: how it works. The worked example persists a lastSeenEventId cursor with packageStorage(), keeps the GitHub credential as a runtime secret reference, and turns the export into a daily cron job. It leaves the job off while patching, checks the manifest and types before publishing, and skips email on quiet days—good scaffolding for idempotent agent jobs. kody

• walgit. Armin Ronacher presented Tobi’s weekend implementation as another case of building hard things with AI; Tobi describes a single Rust binary for S3-compatible object stores using WAL and CAS without another datastore, plus bundle-uri for fast downloads of large repositories. @mitsuhiko +1

Editorial take: The edge is shifting from granting agents more autonomy to engineering the operating loop around them: one human boundary, durable state, bounded execution, and proof that the agent touched the intended code. yegge +2