agentleFS
MicrosoftKnown publishermicrosoft/Copilot-Managed-Runtime/samples/CodeFlow/AGENTS.md

Copilot-Managed-Runtime / CodeFlow

AGENTS.md4 starsChanged 8 days agoMITView on GitHub

CodeFlow is a React + Vite + TypeScript app hosted on Copilot Managed Runtime that reviews GitHub pull requests through the public GitHub connector. Start with README.md. - .github/skills/setup-codeflow/SKILL.md — first-time setup (ms app init, app settings, GitHub connector, .env.local). - .github/skills/add-data-source/SKILL.md — move app data from browser storage to a shared backend. - The sample ships without ms.config.json and connector code generation (generated/, .ms/). Setup creates them (npx ms app init, npx ms app add data-source) in the user's…

  • Reads credentials

The file

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

4 rules. About 0 are common, 0 are distinctive, and 4 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.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    All app-owned data goes through src/storage (collections in src/storage/collections.ts).

    line 21
  2. Very specific:

    Don't use localStorage, sessionStorage or indexedDB directly, and never edit src/storage/core/ (it is shared, synced code).

    line 22
  3. Very specific:

    Don't log payloads, identities or connector responses.

    line 24
  4. Very specific:

    Keep test data synthetic (octo-org/octo-repo#123, octocat, example.com).

    line 26

≈ “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.

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

Agent guide

CodeFlow is a React + Vite + TypeScript app hosted on Copilot Managed Runtime that reviews GitHub pull requests through the public GitHub connector. Start with README.md.

Skills

  • .github/skills/setup-codeflow/SKILL.md — first-time setup (ms app init, app settings, GitHub connector, .env.local).
  • .github/skills/add-data-source/SKILL.md — move app data from browser storage to a shared backend.

Rules

  • The sample ships without ms.config.json and connector code generation (generated/, .ms/). Setup creates them (npx ms app init, npx ms app add data-source) in the user's copy, which is the app's own repository; they are committed there. Only src/connectors/* may import generated/; everything else uses the GitHubClient interface.
  • Anything the connector has no REST operation for goes through GraphQL (githubClient.graphql, via src/services/graphQl.ts). The operation takes no variables: inline values with gqlString and treat any GraphQL errors entry on a mutation as failure.
  • All app-owned data goes through src/storage (collections in src/storage/collections.ts). Don't use localStorage, sessionStorage or indexedDB directly, and never edit src/storage/core/ (it is shared, synced code).
  • Don't log payloads, identities or connector responses; use src/lib/logger.ts.
  • Render external links through safeUrl / githubLink.
  • Keep test data synthetic (octo-org/octo-repo#123, octocat, example.com).

Checks

npm run lint
npm test
npm run typecheck   # after setup (needs generated/)
npm run build       # after setup

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.