agentleFS
Sign inStart free
Vinay-RVinay-R/vibe-engineering-template/AGENTS.md

vibe-engineering-template

AGENTS.md0 starsChanged 27 days agoMITView on GitHub

Auto-injected at session start (SessionStart hook, 9 KB budget): session protocol, STATUS.md Active work + Current status (the latter may be truncated), ARCHITECTURE invariants, the newest decisions/INDEX.md rows — don't re-read those. STATUS Milestones and the worklog index are not injected; open STATUS.md for them. Resumed or compacted session (no hook fired)? Use the session-context skill. Read before structural/code work: the full Vibe Engineering/ARCHITECTURE.md (layout + conventions + gotchas). Decisions + rationale: Vibe Engineering/DECISIONS.md — check before re-deciding anything. History:…

  • 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 31,774 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 repository5 other files it gives its agents.

The file

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

2 rules. About 0 are common, 1 is distinctive, and 1 is 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.

  • 1

    Very specific

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

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

    Never push without explicit user go-ahead: Commit locally, one commit per phase.

    line 21
  2. Distinctive:

    Claim work before starting it: add a row to STATUS.md's Active work table (owner, claimed date, branch, what).

    line 23

≈ “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

{{PROJECT}}

<!-- One paragraph: what the product is and the stack. Keep this file under ~60 lines — it is read by every agent on every session. Detail belongs in Vibe Engineering/. -->

{{ONE_LINE_STACK_DESCRIPTION}}

Auto-injected at session start (SessionStart hook, 9 KB budget): session protocol, STATUS.md Active work + Current status (the latter may be truncated), ARCHITECTURE invariants, the newest decisions/INDEX.md rows — don't re-read those. STATUS Milestones and the worklog index are not injected; open STATUS.md for them. Resumed or compacted session (no hook fired)? Use the session-context skill. Read before structural/code work: the full Vibe Engineering/ARCHITECTURE.md (layout + conventions + gotchas). Decisions + rationale: Vibe Engineering/DECISIONS.md — check before re-deciding anything. History: Vibe Engineering/worklogs/ — dated per-session files; read on demand only. At session end, log the session per the worklog skill. New to the repo? docs/ONBOARDING.md — local setup, access model, workflow.

Hard rules

  • Never push without explicit user go-ahead. Commit locally, one commit per phase. (Sole exception once >1 collaborator: STATUS-only claim/release commits — worklog skill.)
  • Claim work before starting it: add a row to STATUS.md's Active work table (owner, claimed date, branch, what). Don't work on something another row claims.
  • Nothing is "done" until verified per the live-e2e-verify skill: author pass on your local stack (throwaway identities, both sides of every permission boundary, cleanup); the merger runs the live pass.
  • Secrets are server-only; clients get public-prefixed values only.
  • Plans and specs live in Vibe Engineering/plans/, never in a machine-local path.
<!-- Add project-specific hard rules here (migrations, release gates, data handling). A hard rule is one whose violation ships a bug or leaks data; everything else is a convention and belongs in ARCHITECTURE.md § Conventions & gotchas. -->

Commands

  • {{TYPECHECK_CMD}} · {{TEST_CMD}} · {{DEV_CMD}}
  • Context-system lint: scripts/ve-check.sh (run before committing docs)

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.

Check your setup, free