Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Agent Rules Writer: Verified AGENTS.md & CLAUDE.md

    1

    They skip the DCO sign-off that blocks every PR, and they fill space with rules like "write clean code" that no one can check.

    $9

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Agent Rules Writer: Verified AGENTS.md & CLAUDE.md

    Agent Rules Writer: Verified AGENTS.md & CLAUDE.md

    Example session with this skill installed

    Write an AGENTS.md for this repo and make Claude Code use it too. We already have a CLAUDE.md that someone wrote last year.

    • Read your context and instructions
    • Compiled the agent rules writer

    Example session (illustrative).

    Existing files found: CLAUDE.md (64 lines), .cursorrules (12 lines). No AGENTS.md. I audited the existing files first.

    Audit of CLAUDE.md

    SeverityLineFindingFix
    high9npm test: the repo has pnpm-lock.yaml and packageManager: pnpm@9.12.0pnpm test
    highn/aNo sign-off rule, but dco.yml checks every commit and 40 of the last 40 commits are signedAdd git commit -s
    high14npm run e2e: there is no e2e script in package.jsonRemoved (reported below)
    mediumn/aCI also runs pnpm typecheck and pnpm lint --max-warnings 0; the file mentions neitherGate command added
    medium3.cursorrules says to use yarn, which contradicts the lockfileFold into AGENTS.md (Cursor reads it)
    low22-41Twenty lines of general style advice that no one can checkCut

    Commands verified in this session

    • pnpm install --frozen-lockfile: exit 0, 21s
    • pnpm lint --max-warnings 0 && pnpm typecheck && pnpm test: exit 0, 74s (this mirrors ci.yml jobs lint, types, test)
    • pnpm test -- src/billing: exit 0, 6s (fast targeted form)
    • pnpm db:generate: exit 0 (regenerates src/db/generated/)
    • pnpm test:integration: unverified, needs Postgres on :5432 (from docker-compose.yml)

    Never hand-edit: src/db/generated/** (@generated header), vendor/, pnpm-lock.yaml, and CHANGELOG.md, which changesets generates.
    Needs review: openapi.yaml and migrations/ (both owned in CODEOWNERS).

    Proposed changes (diff shown; 96 lines in total):

    • new AGENTS.md with sections Build and verify, Hard rules, Commits and PRs, Layout, Do not
    • CLAUDE.md replaced with @AGENTS.md plus 3 Claude-specific lines
    • .cursorrules removed; Cursor's current docs no longer cover it, and Cursor reads AGENTS.md directly

    Broken command to fix separately: the README also documents npm run e2e, which does not exist.

    Shall I write these changes?

    64 lines), (12 lines). No AGENTS.md

    Connects securely to your tools. The creator never sees your data.

    About this skill

    The problem. Most agent-instruction files are guesses. They say npm test when CI runs pnpm test -- --coverage. They skip the DCO sign-off that blocks every PR, and they fill space with rules like "write clean code" that no one can check. Agents believe what the file says, so one stale command can waste a whole session or produce a PR that fails CI.

    What the agent does.

    • Finds the facts. It reads package.json scripts and the lockfile, Makefile, justfile, Taskfile, Cargo.toml, pyproject.toml, tox and nox configs, pre-commit hooks, and CI workflows (GitHub Actions, GitLab, CircleCI, Azure, Jenkins).
    • Works out the real gate. It writes down the exact local command that matches what CI requires, including flags, toolchain version and environment variables.
    • Gets your conventions from the repo. It reads commit and PR rules from commitlint config, CONTRIBUTING, PR templates and git log, including whether DCO sign-off is enforced.
    • Lists what needs care. Contract files go on a "needs review" list: CODEOWNERS, API schemas, migrations, RFC areas. Generated and vendored paths go on a "never hand-edit" list, each with the command that regenerates it. It also writes a concrete secrets rule.
    • Runs every command it plans to write. A command that needs missing infrastructure is marked # unverified. A command that is simply broken is reported to you and left out.
    • Keeps the output short. The file is imperative, under about 120 lines, and every rule can be checked.
    • Sets up one source of truth. AGENTS.md holds the rules and CLAUDE.md imports it with @AGENTS.md, so the copies don't drift apart.
    • Audit mode. It reviews an existing file and lists stale commands, contradictions with CI or other docs, vague rules, missing essentials and bloat, each with a severity and a suggested fix.
    • Shows you a diff first. Nothing is written until you approve it.

    Who it's for. Maintainers who accept agent PRs, teams adopting Claude Code, Codex, Cursor or Copilot, and anyone whose agents keep running the wrong commands.

    Requirements. An agent that can read files and run shell commands. jq is optional (used to read package.json). Works with any language or build system. AgentHarness is not required.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Prompt & Skill Engineering.

    Cannot verify commands requiring external credentials or Docker if not present. Skips deployment/publishing scripts. Verification is limited to commands that finish within a reasonable timeout.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 17 days ago

    Software
    GitYour project's build and test tooling

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Listed17 days ago

    What's inside

    Frequently Asked Questions

    Codex, Cursor and GitHub Copilot's coding agent read AGENTS.md directly. Claude Code reads CLAUDE.md and pulls in AGENTS.md with an `@AGENTS.md` line (recent versions also read AGENTS.md when no CLAUDE.md exists). Cursor also reads `.cursor/rules/*.mdc`, Copilot reads `.github/copilot-instructions.md`, and Gemini CLI reads GEMINI.md or can be configured to read AGENTS.md. The skill keeps AGENTS.md as the single source and makes the other files point to it.

    Yes. Every command it writes down is run once to prove it works. It never runs deploy, publish, release or anything that pushes. Commands that need services you don't have running are marked unverified instead of being run against real infrastructure.

    Yes. Audit mode produces a table of findings (stale commands, contradictions with CI, vague rules, missing essentials) with a severity and a fix for each one. You decide what to apply.

    No. It works on any repository using only file reads and shell commands. AgentHarness is a separate open-source tool from the same author.

    No. It shows you a diff and waits for your approval before writing any instruction file. It never edits CI, hooks or CONTRIBUTING to match what it wrote. It reports any mismatch instead.

    New in Prompt & Skill Engineering