agent-skills
AGENTS.md2 starsChanged 10 days agoMITView on GitHub
Read docs/worktrees.md and docs/pull-request-standard.md. This is a skill collection, with no app/backend, package install, build, ports or dev services. Do not introduce Convex. Keep lifecycle modules and tests under scripts/worktree/. Never reset, stash or discard user changes. Setup fetches origin and only fast-forwards. Run focused checks sequentially with NODE_OPTIONS=--max-old-space-size=512 for Node. Full lint/typecheck/build belongs on UbiCloud CI. Use only ubicloud-standard-2-ubuntu-2404 Linux CI runners. Serialize dependency installs/codegen/backend integration with flock -w 3600 /home/cloudagent/.cache/fantastic-heavy.lock. Write-token metadata jobs must execute trusted base code…
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 31,843 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 repository27 other files it gives its agents.
- cmux-agent-orchestratorSkill
- cmux-pr-qc-agentSkill
- cmuxSkill
- finchSkill
- peekSkill
- gmail-inbox-zero-triageSkill
- gmail-oib-zeroSkill
- whatsapp-triageSkill
- add-to-changelogSkill
- check-prSkill
- cli-reviewSkill
- coderabbit-requestSkill
- convex-domain-folderSkill
- e2e-remote-setupSkill
- greploopSkill
- update-docsSkill
- antigravity-cliSkill
- social-captureSkill
- check-model-usageSkill
- code-structureSkill
- evidence-driven-testingSkill
- interviewSkill
- issue-breakdownSkill
- linear-labelsSkill
- model-classifierSkill
- remotion-explainer-videoSkill
- skill-makerSkill
The file
We split this AGENTS.md into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 5
Run focused checks sequentially with NODE_OPTIONS=--max-old-space-size=512 for Node.
- Distinctive: line 7
Write-token metadata jobs must execute trusted base code only.
- Very specific: line 9
All local Node test suites must hold /home/cloudagent/.cache/fantastic-heavy.lock for the entire subprocess tree:
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 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
Repository instructions
Read docs/worktrees.md and docs/pull-request-standard.md. This is a skill collection, with no app/backend, package install, build, ports or dev services. Do not introduce Convex. Keep lifecycle modules and tests under scripts/worktree/. Never reset, stash or discard user changes. Setup fetches origin and only fast-forwards.
Run focused checks sequentially with NODE_OPTIONS=--max-old-space-size=512 for Node. Full lint/typecheck/build belongs on UbiCloud CI. Use only ubicloud-standard-2-ubuntu-2404 Linux CI runners. Serialize dependency installs/codegen/backend integration with flock -w 3600 /home/cloudagent/.cache/fantastic-heavy.lock.
Write-token metadata jobs must execute trusted base code only. PRs need the owning ticket after the title colon, five ordered sections, actual agent/session identity, accessible evidence and acceptance checklist. Never claim skipped checks passed.
All local Node test suites must hold /home/cloudagent/.cache/fantastic-heavy.lock for the entire subprocess tree: flock -w 3600 /home/cloudagent/.cache/fantastic-heavy.lock env NODE_OPTIONS=--max-old-space-size=512 node --test --test-concurrency=1 <specific test files>. Do not nest this lock.
The shared lock requirement applies to all local test suites, including Python suites and toolkit checks. CI runners are separate from this shared VPS.
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.