openclaw-android-node-apk
AGENTS.md59 starsChanged 16 days agoMITView on GitHub
Own docs authoring, published links, docs i18n policy.
We split this AGENTS.md into the rules it gives an agent
5 rules. About 1 is common, 0 are distinctive, and 4 are very specific to this project.
≈1
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 11
Never generically format generated CHANGELOG/ or root changelog.
- Common: line 27
Follow Secret Placeholder Conventions.
- Very specific: line 34
Never hand-edit docs/plugins/reference/, docs/plugins/reference.md, docs/plugins/plugin-inventory.md.
- Very specific: line 35
Only source stub in docs/docs_map.md.
- Very specific: line 53
Before publish-repo sync/scripts/docs-i18n: update English + glossary here.
≈ “Common” is an estimate: at least 1 in 5 of the 36,368 AGENTS.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.
Files
Docs Guide
Own docs authoring, published links, docs i18n policy.
Source Ownership
- Author
/clawhub/**in openclaw/clawhub, never here.scripts/docs-sync-publish.mjsreplaces publishdocs/clawhub/tree. Link audits accept routes declared indocs/docs.jsonwithout checkout; undeclared routes fail. - OpenClaw-specific skill/plugin installation, update, verification, removal, release-trust guidance stays here (
docs/cli/skills.md,docs/cli/plugins.md). Standalone ClawHub CLI/publishing reference → upstream. - Plain
pnpm docs:check-linksskips ClawHub fragments. Usepnpm docs:check-links:anchors+OPENCLAW_DOCS_SYNC_CLAWHUB_REPOset to source checkout; otherwise declared-route fragments unverified. - Approved release-doc changes: regenerate complete marked
CHANGELOG/<version>.mdmirror viapnpm changelog:from-docs; preserve ordered sources + frozenCHANGELOG/records/<version>.md. Usepnpm changelog:check; untouched history not converted. Generation/post-release publication: readopenclaw-changelog-updateskill. - Never generically format generated
CHANGELOG/**or root changelog; exact migrated/mirrored bytes generator-owned.
Local Preview
- Uncommitted English content in current website UI:
pnpm docs:dev -- --page <route>; repeat--pageup to 30 pages. Re-run after edits. - Clone
openclaw/docsas../openclaw-docsbeside main checkout; runnpm cithere. Override:--site-repo <path>orOPENCLAW_DOCS_SITE_REPO. - Preview writes only ignored
.cache/docs-preview/; no sync/translate/publish. Build-only/port options:pnpm docs:dev --help. Serving needs Python 3. - Website styling/renderer →
openclaw/docs; content, navigation, redirects, shared publishing parser → here.
Published Link Rules
openclaw/docspublisheshttps://docs.openclaw.ai; owns design/UI.- Internal
docs/**/*.mdlinks: root-relative, no.md/.mdx, including section anchors:[Hooks](/gateway/config-hooks#hooks). - Heading IDs:
scripts/lib/docs-markdown.mjs; verify viapnpm docs:check-links:anchors. Preserve published IDs + named anchors; compatibility aliases never replace existing targets. Heading wording may change →<a id="stable-section-name" />. - README/other GitHub-rendered docs: absolute docs URLs.
- Public docs generic: no personal devices, hostnames, local paths. Placeholders:
user@gateway-host,~/path/to/skills. - Follow Secret Placeholder Conventions; credential examples obviously fake.
Docs Content Rules
- Runtime-floor changes in
node-version.mjs,package.jsonengines,src/infra/runtime-guard.ts(Bun), orsrc/infra/sqlite-runtime-version.ts: update supported-version/history tables indocs/install/node-compatibility.md+docs/install/bun-compatibility.md. - Alphabetize services/providers in docs, UI copy, pickers, except explicit runtime/auto-detection order. Follow root
AGENTS.mdplugin terminology. - CI schema-checks JSON/JSON5 fences resembling whole
openclaw.jsonfiles (pnpm docs:check-config-examples). Deliberately partial/legacy fences:validate=false. - Never hand-edit
docs/plugins/reference/**,docs/plugins/reference.md,docs/plugins/plugin-inventory.md; runpnpm plugins:inventory:gen.docs/maturity/**: see below. - Only source stub in
docs/docs_map.md; publishing/packaging generate expanded map frompnpm docs:list --headings. Never commit heading mirror.
Internal Docs
- Long-lived private operator docs → private operator repo. Local scratch/mirrors may use ignored
docs/internal/; never link from public docs or include indocs/docs.json. scripts/docs-sync-publish.mjsexcludes/prunesdocs/internal/**+ rootdocs/AGENTS.md/docs/CLAUDE.md; translation finalization removes locale copies of instruction files. Publicdocs/reference/templates/**remain published.- Internal docs may name repo paths, private apps, 1Password items, runbooks; never secret values.
Maturity Scorecard Editing
- Edit
taxonomy.yaml+qa/maturity-scores.yaml, never generated score, LTS, taxonomy, QA-profile, evidence tables indocs/maturity/. - Generation owner:
scripts/qa/render-maturity-docs.ts; refresh:pnpm maturity:render; verify:pnpm maturity:check. .github/workflows/maturity-scorecard.ymlrenders previews/can open generated-doc PRs;.github/workflows/openclaw-release-checks.ymldispatches it for release QA.- Deterministic
qa-evidence.json.scorecardstays in Actions artifacts unless maintainer requests sanitized committed projection. Human overrides: source-state PR with reasons + public/redacted evidence.
Docs i18n
- English docs/glossary here authoritative (ClawHub: Source Ownership). Never add/edit
docs/<locale>/**here; generated translations +docs/.i18n/*.tm.jsonl→openclaw/docs. - Before publish-repo sync/
scripts/docs-i18n: update English + glossary here. Before rerunning translation: entries for new technical terms, page titles, short nav labels, terms requiring fixed translation/English spelling. - Changed English titles/short internal labels:
pnpm docs:check-i18n-glossary. Pipeline: readdocs/.i18n/README.md.
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 28,693 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository107 other files it gives its agents.
- AGENTS.mdAGENTS.md
- extensions/AGENTS.mdAGENTS.md
- scripts/AGENTS.mdAGENTS.md
- test/AGENTS.mdAGENTS.md
- ui/AGENTS.mdAGENTS.md
- agent-transcriptSkill
- auto-qaSkill
- autoreviewSkill
- channel-message-flowsSkill
- clawdtributorSkill
- claw-scoreSkill
- clawsweeperSkill
- control-ui-e2eSkill
- crabboxSkill
- discord-clawdSkill
- discord-e2eSkill
- discord-user-postSkill
- discrawlSkill
- gitcrawlSkill
- graincrawlSkill
- notcrawlSkill
- openclaw-changelog-updateSkill
- openclaw-ci-limitsSkill
- openclaw-debuggingSkill
- openclaw-docker-e2e-authoringSkill
- openclaw-ghsa-maintainerSkill
- openclaw-live-updaterSkill
- openclaw-parallels-smokeSkill
- openclaw-pr-maintainerSkill
- openclaw-qa-testingSkill
- openclaw-refactor-docsSkill
- openclaw-release-validationSkill
- openclaw-repair-sweepSkill
- openclaw-secret-scanning-maintainerSkill
- openclaw-test-heap-leaksSkill
- openclaw-testingSkill
- openclaw-test-performanceSkill
- openclaw-updateSkill
- parallels-discord-roundtripSkill
- plugin-sdk-impactSkill
- proof-videoSkill
- prototype-openclaw-tuiSkill
- pr-simplifySkill
- release-openclaw-announcementSkill
- release-openclaw-ciSkill
- release-openclaw-macSkill
- release-openclaw-maintainerSkill
- release-openclaw-plugin-testingSkill
- security-triageSkill
- slack-e2eSkill
- slacrawlSkill
- solidSkill
- tag-duplicate-prs-issuesSkill
- technical-documentationSkill
- telegram-e2e-userbotSkill
- test-auditSkill
- update-team-serverSkill
- verify-releaseSkill
- 1passwordSkill
- apple-notesSkill
- The first 60 shown.
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
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.

