grainulator
AGENTS.md86 starsChanged 9 days agoMITView on GitHub
This is the Grainulator source checkout. Follow the user’s active scope for local edits, branch pushes, deployment, publication, and repository archival. Do not create a release tag or publish a release before the required CI checks pass; those actions must also be covered by the user’s release authorization. The root npm package and component workspaces remain private; a GitHub release does not authorize npm publication. Use the active sprint directory identified by the current task or project instructions. If none…
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 repository20 other files it gives its agents.
- analyticsSkill
- blind-spotSkill
- briefSkill
- calibrateSkill
- challengeSkill
- feedbackSkill
- fetchSkill
- grainulatorSkill
- healthcheckSkill
- initSkill
- orchestrateSkill
- presentSkill
- pullSkill
- researchSkill
- resolveSkill
- routerSkill
- setupSkill
- statusSkill
- syncSkill
- witnessSkill
The file
We split this AGENTS.md into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
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
Use the active sprint directory identified by the current task or project instructions.
- Very specific: line 9
Run npm test for component suites and dogfood regressions.
≈ “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
Grainulator workspace
This is the Grainulator source checkout. Follow the user’s active scope for local edits, branch pushes, deployment, publication, and repository archival. Do not create a release tag or publish a release before the required CI checks pass; those actions must also be covered by the user’s release authorization. The root npm package and component workspaces remain private; a GitHub release does not authorize npm publication.
Use the active sprint directory identified by the current task or project instructions. If none exists, create a dedicated sprint for the requested work; never repurpose an unrelated ledger. Pass --dir or the MCP dir argument explicitly. Use skills/grainulator/SKILL.md for the portable workflow.
Source imports and local-edit provenance live in docs/source-imports.json. Do not overwrite original checkouts. Retained package names are compatibility aliases; package directories describe responsibilities.
Run npm test for component suites and dogfood regressions. Run node test/conformance.mjs from packages/runtime for Rust runtime conformance. Use npm run dev for the local research playground and npm run test:playground for responsive and keyboard checks. Public website code and deployment belong to grainulation/infra.
The permission dashboard and its connectors have been removed at the maintainer’s request. Do not restore that application, its hooks, or its runtime dependencies. Native hosts own permissions and remote access. Generated evidence and analytics reports remain supported.
Next-step output
After a meaningful pass, use the current compiler's next_actions to present exactly two bullet lists labeled Auto and Manual. Auto is work the agent can continue under existing authorization. Manual is only work requiring the user's decision, access, or action. Classify using the current request and constraints; compiler suggestions never grant permission. Continue authorized Auto work without asking again.
Keep 2–3 useful actions total when available, use short concrete labels and commands where useful, and show None. for an empty group. Do not invent work to fill a quota. Never omit next steps merely because compilation is ready or the answer should be brief. Refresh stale compilation first and exclude work the user removed from scope. When the user asks only for next steps, output only these two lists: no findings recap, counts, reasons, or offer to continue.
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.