trivoallantrivoallan/ontrack/AGENTS.md

ontrack

AGENTS.md1 starsChanged yesterdayApache-2.0View on GitHub

When asked to review, rule on or supersede an ADR, run npx ontrack review [adr] and follow its output.

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 31,439 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 repository12 other files it gives its agents.
- openspec-apply-changeSkill
- openspec-archive-changeSkill
- openspec-bulk-archive-changeSkill
- openspec-continue-changeSkill
- openspec-exploreSkill
- openspec-ff-changeSkill
- openspec-new-changeSkill
- openspec-onboardSkill
- openspec-proposeSkill
- openspec-sync-specsSkill
- openspec-update-changeSkill
- openspec-verify-changeSkill

The file

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

1 rule. About 0 are common, 0 are distinctive, and 1 is 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.
1
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Very specific:
When asked to review, rule on or supersede an ADR, run npx ontrack review [adr] and follow its output.
line 4

≈ “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 rules (ontrack)

When asked to review, rule on or supersede an ADR, run npx ontrack review [adr] and follow its output.

The engineering track skips the cooldown (local/ADR-0024-the-engineering-track-skips-the-cooldown)

dependencies:
  updater: dependabot
  automerge: patch
admission:
  approver: person
  install_scripts: ignored

Record architecture decisions (trivoallan/ADR-0001-record-architecture-decisions)

record-architecture-decisions:
  format: nygard

Localization (trivoallan/ADR-0002-localization)

localization:
  language:
    default: english
    documentation:
    commits:
    code:
    comments:

Software architecture (trivoallan/ADR-0003-architecture)

architecture:
  pattern: monolithic

Languages (trivoallan/ADR-0004-languages)

languages:
  main:
    name: TypeScript

Validation (trivoallan/ADR-0005-validation)

validation:
  boundary: zod
  data_files: json-schema

Commits (trivoallan/ADR-0006-commits)

commits:
  scopes: [apply, check, cli, governance, instructions, openspec, plan, review, revision, tracks]
  tool: commitlint

Tests (trivoallan/ADR-0007-tests)

tests:
  coverage_target: 95

Documentation (trivoallan/ADR-0008-documentation)

docs:
  tool: starlight
  root: docs/
  audience: public
  channels: [release, main]

Branching (trivoallan/ADR-0009-branching)

branching:
  model: github-flow
  merge: squash
  prefixes: [feat, fix, docs, chore]

Architecture documentation (trivoallan/ADR-0010-architecture-documentation)

architecture:
  document: arc42
  model: likec4
  diagrams: mermaid

Forge and continuous integration (trivoallan/ADR-0011-forge-and-ci)

forge:
  gate: blocking
  audit: zizmor

Delivery (trivoallan/ADR-0012-delivery)

delivery:
  target: package
  environments:
    - { name: github, trigger: tag }
    - { name: npm, trigger: tag }
  release_tool: release-please
  release_notes: highlights
  registry: none
deployment:
  manifests: none

Work tracking (trivoallan/ADR-0014-work-tracking)

tracking:
  tool: github-issues
  project: trivoallan/ontrack

Secrets (trivoallan/ADR-0015-secrets)

secrets:
  storage: keychain
  guard: gitleaks

Changes (trivoallan/ADR-0016-changes)

changes:
  framework: openspec
  schema: spec-driven-with-adr

Agent tooling (trivoallan/ADR-0017-agent-tooling)

agent:
  hosts: [claude-code]

Vulnerabilities (trivoallan/ADR-0019-vulnerabilities)

vulnerabilities:
  sbom: cyclonedx
  scanner: grype
  fail_on: critical

Build provenance (trivoallan/ADR-0021-build-provenance)

supply_chain:
  build_level: 2

Review and merge (trivoallan/ADR-0022-review-and-merge)

review:
  by: maintainer
  approvals: 0

License (trivoallan/ADR-0023-license)

license:
  spdx: Apache-2.0

Code scanning (trivoallan/ADR-0024-code-scanning)

code_scanning:
  tool: codeql
  fail_on: high

Tools outside the package manager (trivoallan/ADR-0025-tools)

tools:
  manager: mise

Agent identity (trivoallan/ADR-0026-agent-identity)

agent:
  identity: maintainer

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