agentleFS
brayandiazcbrayandiazc/project-starter-template-en-ai/AGENTS.md

project-starter-template-en-ai

AGENTS.md2 starsChanged 2 months agoMITView on GitHub

Instructions for the AI coding agents working in this repository. [One or two lines on what this project is and does.] The full documentation lives in docs/ — this file is its only index; read it before any non-trivial work. architecture/ vs conventions/: architecture/ answers what this project builds (its data model, its API, its screens); conventions/ answers how the work is done (how it is tested, how it is deployed, how secrets are handled). Both are filled in when…

  • Reads credentials

The file

Show its rules and text

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

13 rules. About 0 are common, 4 are distinctive, and 9 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 9

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Very specific:

    Accompany actively: Ask when scope or priority is ambiguous instead of assuming.

    line 63
  2. Very specific:

    No spec, no change (mandatory): Every feature or fix (feat/*, fix/*) is born from a spec in specs/ sharing the branch's slug (create it …

    line 67
  3. Very specific:

    Issues and PRs from the templates: When creating an issue or a pull request, ALWAYS use the templates in .github/ (ISSUE_TEMPLATE/ and …

    line 81
  4. Very specific:

    Tests with every change: Follow docs/conventions/testing.md.

    line 86
  5. Very specific:

    "Done" has a definition: Before calling a change done, go through docs/conventions/definition-of-done.md.

    line 87
  6. Very specific:

    Keep the documentation in sync: Update the relevant docs/ and CHANGELOG.md.

    line 89
  7. Very specific:

    Never leave a change undocumented: every change updates CHANGELOG.md and the affected docs/ in the same PR, and every implemented spec …

    line 94
  8. Very specific:

    Never commit secrets or real .env values.

    line 99
  9. Distinctive:

    Never invent dependencies, files or APIs — verify they exist first.

    line 101
  10. Very specific:

    Never edit code on a feat/*/fix/* branch without its spec in specs/, nor create work branches off main — the hooks block those two rules.

    line 102
  11. Distinctive:

    Never bypass authorization checks or weaken security to make something work.

    line 104
  12. Distinctive:

    Never push to main or force-push to shared branches.

    line 105
  13. Distinctive:

    Do not reformat unrelated code or make sweeping changes outside the task.

    line 106

≈ “Common” is an estimate: at least 1 in 5 of the 41,581 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
<!-- Canonical instructions for [PROJECT_NAME]'s agents. This is the single source of truth for AI coding agents (Claude Code, Copilot, Cursor, etc.). CLAUDE.md imports this file. Keep it concise (<150 lines) and include only non-obvious, project-specific guidance — people read the README. -->

AGENTS.md — [PROJECT_NAME]

Instructions for the AI coding agents working in this repository.

Project summary

[One or two lines on what this project is and does.] The full documentation lives in docs/ — this file is its only index; read it before any non-trivial work.

Repository map (read this first)

You need to know…Read
How to work here without reviewing codedocs/conventions/ai-agents.md
The work cycle, from spec to releasedocs/conventions/workflow.md
Why the product exists and how it is paiddocs/product/business-model.md
What is done and what comes nextdocs/product/roadmap.md
Which stack was chosen heredocs/architecture/stack.md
How the system is builtdocs/architecture/architecture.md
Data modeldocs/architecture/database.md
Authentication and permissionsdocs/architecture/auth.md
The API contractdocs/architecture/api.md
Which screens exist and where each one isdocs/architecture/screens.md
How we write codedocs/conventions/
Why each decision was takendocs/decisions/
Visual identity and tokensdesign/
The design system, for AI agentsDESIGN.md

architecture/ vs conventions/: architecture/ answers what this project builds (its data model, its API, its screens); conventions/ answers how the work is done (how it is tested, how it is deployed, how secrets are handled). Both are filled in when instantiating — the difference is not "reusable vs own" but the question they answer. When a topic does not warrant both questions, it lives in a single document (auth lives entirely in architecture/auth.md, rules included); only the database keeps the pair, and each rule lives on exactly one side.

Why design/ is not inside docs/: docs/ is what you read to build; design/ is consumed — design/tokens.css is imported by the application's CSS. When the project has an application, its content will migrate inside it (app/assets/) and only its guide will stay at the root.

Always defer to docs/conventions/ for style and rules — they are the source of truth, not your priors.

Setup & commands

[INSTALL_DEPENDENCIES_COMMAND]   # install dependencies
[START_DEV_COMMAND]              # run locally
[TEST_COMMAND]                   # run the test suite
[LINT_COMMAND]                   # lint / format

Working agreement

  • Accompany actively. Ask when scope or priority is ambiguous instead of assuming; suggest what the person did not ask for but will need. Priority is set by docs/product/roadmap.md. The full cycle is in docs/conventions/workflow.md.
  • No spec, no change (mandatory). Every feature or fix (feat/*, fix/*) is born from a spec in specs/ sharing the branch's slug (create it with /new-spec or delegate to the architect subagent), and its proposal.md declares which roadmap item it completes. The spec-guardrails.sh hook guarantees it: with no spec —or with a half-filled proposal.md— you cannot edit code.
  • Follow Git Flow. Work branches (feat/…, fix/…, docs/…, chore/…) are ALWAYS born off develop, never off main (only hotfix/* starts from main). If develop does not exist, create it from main and publish it before any work. See CONTRIBUTING.md. Never commit directly to main or develop. The git-guardrails.sh hook blocks the violations.
  • Code is written in English. Variables, functions, classes, files, tables, columns and paths go in English, regardless of the project's or the conversation's language.
  • Conventional Commits. type(scope): summary. Add the AI co-author line for AI-assisted commits (see docs/conventions/ai-agents.md).
  • Issues and PRs from the templates. When creating an issue or a pull request, ALWAYS use the templates in .github/ (ISSUE_TEMPLATE/ and PULL_REQUEST_TEMPLATE.md) and respect the branching in CONTRIBUTING.md. The /open-issue and /open-pr skills do it for you.
  • Tests with every change. Follow docs/conventions/testing.md.
  • "Done" has a definition. Before calling a change done, go through docs/conventions/definition-of-done.md.
  • Keep the documentation in sync. Update the relevant docs/ and CHANGELOG.md; record notable decisions as an ADR in docs/decisions/.

Strict rules — never do this

  • Never leave a change undocumented: every change updates CHANGELOG.md and the affected docs/ in the same PR, and every implemented spec ticks its item in docs/product/roadmap.md; every notable decision leaves an ADR. A change with no documentation is not done — the changelog job in quality.yml verifies it on every PR.
  • Never commit secrets or real .env values. See SECURITY.md and docs/conventions/secrets.md.
  • Never invent dependencies, files or APIs — verify they exist first.
  • Never edit code on a feat/*/fix/* branch without its spec in specs/, nor create work branches off main — the hooks block those two rules.
  • Never bypass authorization checks or weaken security to make something work.
  • Never push to main or force-push to shared branches.
  • Do not reformat unrelated code or make sweeping changes outside the task.

AI assistants and tooling

  • This file is the canonical context and the single documentation index. Tool-specific files (CLAUDE.md, etc.) point here.
  • The subagents live in .claude/agents/ and the skills in .claude/skills/. Interviews and anything that requires asking the person something go in a skill: a subagent runs in its own context and has no way to ask anything.
  • Working method, where to verify and where you fail silently: docs/conventions/ai-agents.md.

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.