agentleFS
Sign inStart free
ZenRowsZenRows/cli/AGENTS.md

cli

AGENTS.md16 starsChanged 27 days agoMITView on GitHub

Instructions for coding agents working on this repository: the Zenrows CLI (@zenrows/cli) and the agent skills, templates, workflows, recipes and evals it ships. To use Zenrows from an agent instead, install the skills: npx skills add ZenRows/cli. CI runs typecheck and test on Node 20 and 22. Run both before pushing. npm run test:e2e hits the live API and bills the key's account; see docs/contributing.md before running it. - TypeScript with zero runtime dependencies. Use fetch, node:util parseArgs, node:fs, node:crypto.…

  • 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 repository10 other files it gives its agents.

The file

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

5 rules. About 1 is common, 1 is distinctive, and 3 are very specific to this project.

  • ≈1

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Common:

    Never print or persist an API key.

    line 26
  2. Very specific:

    Every error is agent-actionable: code, message, likely_cause, next_action, optional suggested_commands.

    line 27
  3. Distinctive:

    Never fake backend behaviour.

    line 29
  4. Very specific:

    No trailer lines (Co-authored-by, Signed-off-by, ...), no issue-tracker keys, and no "generated with/by" AI attribution, in commits, PR …

    line 44
  5. Very specific:

    Never edit the version in package.json, package-lock.json or CLI_VERSION in src/core/config.ts.

    line 50

≈ “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

AGENTS.md

Instructions for coding agents working on this repository: the Zenrows CLI (@zenrows/cli) and the agent skills, templates, workflows, recipes and evals it ships. To use Zenrows from an agent instead, install the skills: npx skills add ZenRows/cli.

Commands

npm ci
npm run typecheck   # tsc --noEmit
npm test            # builds to dist/, then runs node:test
npm run dev -- --help

CI runs typecheck and test on Node 20 and 22. Run both before pushing. npm run test:e2e hits the live API and bills the key's account; see docs/contributing.md before running it.

Code

  • TypeScript with zero runtime dependencies. Use fetch, node:util parseArgs, node:fs, node:crypto. Do not add a runtime dependency.
  • Layout and the steps for adding a primitive: docs/contributing.md.
  • Never print or persist an API key. Redact secrets in logs and artifacts.
  • Every error is agent-actionable: code, message, likely_cause, next_action, optional suggested_commands.
  • Never fake backend behaviour; return a normalized error instead.

Skills

  • skills/*/SKILL.md are the CLI's skills; agent-plugin/skills/ are the MCP-native copies for the agent plugin. Change both when a fact changes.
  • Quote any frontmatter value that contains : . Strict YAML parsers, such as the one behind npx skills add, skip the whole skill otherwise; a test checks this.

Commits and pull requests (CI enforces these)

  • Conventional Commits in commit messages and the PR title: type(scope): subject. fix, feat and perf need a lowercase scope.
  • The subject says why the change is needed, not what the diff does.
  • No trailer lines (Co-authored-by, Signed-off-by, ...), no issue-tracker keys, and no "generated with/by" AI attribution, in commits, PR title or PR body.

Releases

  • Never edit the version in package.json, package-lock.json or CLI_VERSION in src/core/config.ts. release-please sets them.
  • Merging the chore: release X.Y.Z PR tags, releases and publishes to npm. Recovery when a release fails: docs/contributing.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.

Check your setup, free