agentleFS
ai-ecoverseai-ecoverse/slicc/docs/CLAUDE.md

slicc

CLAUDE.md37 starsChanged 20 days agoApache-2.0View on GitHub

This file covers the documentation surface in docs/. All package CLAUDE.md files are now within the 20,000-char cap. The grandfathered exemption list in check-doc-sizes-lib.mjs is empty. Exemption values may only be lowered or deleted — never added or raised. Do not add "Added in PR #NNN" or "Changed in PR #NNN" lines to CLAUDE.md files. Provenance belongs in git log; durable lessons (gotchas, anti-patterns, decisions) belong in docs/pitfalls.md or docs/review-patterns.md, not inline breadcrumbs. Deep implementation detail that does not fit…

The file

We split this CLAUDE.md into the rules it gives an agent

6 rules. About 0 are common, 3 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Update the nearest package CLAUDE.md when a change is package-specific.

    line 16
  2. Distinctive:

    Update the root CLAUDE.md only for repo-wide navigation, CI gates, or cross-cutting principles.

    line 17
  3. Very specific:

    Put long-form implementation detail in the appropriate docs/*.md file rather than bloating a CLAUDE.md.

    line 18
  4. Very specific:

    All package CLAUDE.md files are now within the 20,000-char cap.

    line 29
  5. Very specific:

    Do not add "Added in PR #NNN" or "Changed in PR #NNN" lines to CLAUDE.md files.

    line 35
  6. Distinctive:

    Keep this directory explanatory, not redundant: prefer one authoritative page per topic and link to it from the shorter CLAUDE.md files.

    line 89

≈ “Common” is an estimate: at least 1 in 5 of the 28,029 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
CLAUDE.md

CLAUDE.md

This file covers the documentation surface in docs/.

Documentation Tiers

TierPrimary file/locationPurpose
PublicREADME.mdUser-facing overview and onboarding
Developmentroot and package CLAUDE.md filesHigh-signal developer guidance and package navigation
Agent referencedocs/Detailed architecture, commands, patterns, pitfalls, and workflows
Developer agent skills.agents/skills/*/SKILL.mdRepo procedures for verification, feature wiring, tests, and operations runbooks

How to Update Docs

  • Update the nearest package CLAUDE.md when a change is package-specific.
  • Update the root CLAUDE.md only for repo-wide navigation, CI gates, or cross-cutting principles.
  • Put long-form implementation detail in the appropriate docs/*.md file rather than bloating a CLAUDE.md.

Size budgets (enforced by npm run lint:docs)

FileLimitUnitNote
CLAUDE.md (root)15,000charsenforced
packages/*/CLAUDE.md20,000charsenforced
packages/vfs-root/shared/CLAUDE.md2,048bytesbundled into the VFS
.github/copilot-instructions.md + *.instructions.md4,000charsCopilot truncation limit

All package CLAUDE.md files are now within the 20,000-char cap. The grandfathered exemption list in check-doc-sizes-lib.mjs is empty. Exemption values may only be lowered or deleted — never added or raised.

No PR breadcrumbs

Do not add "Added in PR #NNN" or "Changed in PR #NNN" lines to CLAUDE.md files. Provenance belongs in git log; durable lessons (gotchas, anti-patterns, decisions) belong in docs/pitfalls.md or docs/review-patterns.md, not inline breadcrumbs. Deep implementation detail that does not fit the budget should move to docs/, not shrink to a one-liner in a CLAUDE.md.

Common Destinations in docs/

Architecture and build:

  • architecture.md — detailed subsystem/file maps, layer stack, IndexedDB inventory, tray/sync matrix (opens with architecture-diagram.png, the float topology overview)
  • development.md — build, run, and debug workflows
  • writing-slicc-tests — testing patterns and command selection
  • verifying-before-push — pre-push/PR validation pass: lint internals, the boy-scout debt gate, coverage floors, and other CI-only gates
  • adding-slicc-features — how to add a new shell command, tool, provider, sprinkle, etc.
  • kernel/process-model.md — kernel-host / process-manager deep reference
  • work-unit.md — ADR for #1666: cone and scoop as roles over one WorkUnit runtime; policy table, invariants, migration phases
  • gelatiere.md — the gelatiere, SLICC's resident advisor: a persistent root unit that reviews sessions nightly and after a chat ends and suggests skills and use cases; why it is a root, stores, delivery, the welcome-card stream
  • layouts.md — the panel system (SliccPanel + <slicc-layout>), layout documents and their two VFS roots, the layout shell command, locking, the Cherry-pushed-layout wire path, and the dock-tree it supersedes
  • feature-flags.md — typed registry, worker overlays, Cherry host keys, lint:dead-flags, and the propose → graduate → retire path
  • panel-system-design.md — why the panel system is shaped the way it is: the trust model for agent-authored panels, docked-vs-floating, and the two hardening measures (approval-path capture, trusted layer)

Subsystems:

  • shell-reference.md — shell command reference (authoritative per-command list)
  • computer-protocol.md — computer wire types, registry, adapters (v86 / tab / jsh), screenshot-space coords
  • playwright-cli-sync.md — how Slicc's playwright-cli stays aligned with the official @playwright/cli: the sync script, the Slicc command manifest, when to run, and how to add a new command
  • tools-reference.md — agent tool surface reference
  • mounts.md — mount setup for local FS Access, S3/R2/MinIO, and Adobe da.live
  • secrets.md — secrets storage, masking, and domain-scoped injection
  • approvals.md — capability approval gates: shared pattern + authority axis, sudo policy, device & gesture gates, OS capture gates
  • oauth-intercept.md — provider OAuth intercept and silent renewal
  • operational-telemetry.md — Helix RUM beacons and debug sampling
  • slicc-handoff.md — external handoff protocol (RFC 8288 Link header + navigate lick)
  • .agents/skills/deploying-tray-worker/SKILL.md — tray hub ops runbook: R2 asset archive setup, deploy-gating, ghost-leader reconnect, CI retry logic, and staging test guide
  • link-discovery.md — the standalone discover shell command and the --discover flag on playwright-cli subcommands (fetch, goto, navigate, open, tab-new); covers RFC 8288 / RFC 9727 parsing, emission, and the SLICC handoff/upskill rels
  • urls.md — production URL inventory
  • electron.md — Electron float workflow
  • sliccstart-browser.md — Sliccstart's browser-like surfaces: the macOS default-browser role (registration, Info.plist declarations, incoming-link routing over CDP) and previous-session tab restore
  • ios-simulator-qa.md — hand-running the iOS follower in a Simulator: boot/build/install/launch, seeding @AppStorage via launch arguments, getting a real Join URL
  • bench-runner.md — benchmark runner internals: judge (incl. fallback), none-skills flag, transcript collection over the 8 MiB tray limit, leader lifecycle and diagnostics, publishing pipeline

Review & gotchas:

  • pitfalls.md — runtime and extension gotchas (CSP, dual-mode runtime detection, WASM heap views, etc.)
  • review-patterns.md — source of truth for the automated PR reviewers (Claude action, Codex, Copilot): the numbered blind-spot categories, the five-runtime parity matrix, and the severity rubric

Other:

  • exploration/ — open design notes (not load-bearing reference)
  • screenshots/ — image assets used by README and other docs

Planning artifacts (docs/superpowers/specs/, docs/superpowers/plans/) are intentionally not kept on main — .gitignore keeps them out. Keep them local or in the PR description.

Keep this directory explanatory, not redundant: prefer one authoritative page per topic and link to it from the shorter CLAUDE.md files.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.