AgentsMD CheckerBack to checker ↗
BUILD LOG

What the checker does, and what it does not claim.

This is the dated product record for AgentsMD Checker. It describes tested behavior, the sample shown in the tool, and work that still depends on external accounts or real-user evidence.

First published August 1, 2026 · Updated August 2, 2026 · AgentsMD Checker

Why this project exists

A repository can accumulate several instruction files as teams switch or combine coding agents. The files often look individually reasonable while disagreeing on package manager, test command, delivery rules, or directory scope. This checker handles that narrow problem. It does not claim that a Markdown file can enforce model behavior.

What is tested today

  • @AGENTS.md is treated as inheritance, not duplicated content.
  • Claude-specific lines are preserved when a shared AGENTS.md is generated.
  • Package-manager disagreements and likely positive/negative rule conflicts are flagged.
  • A missing AGENTS.md import target is reported as a critical finding.
  • Generated Markdown is copied and downloaded in the browser.
  • Free-checker file contents have no upload route and are never written to the database.

The project's release checks run a production build, rendered-page tests, checker behavior tests, linting, and strict TypeScript validation.

The worked example in the checker

This is a demonstration shipped with the product, not a customer result. The sample AGENTS.md says to use pnpm and not push directly to main. The sample CLAUDE.md says to use npm and to push directly to main after the task.

AGENTS.md sample
- Use pnpm install.
- Run pnpm test and pnpm lint.
- Do not push directly to main.
CLAUDE.md sample
- Use npm install.
- Run npm test.
- Push directly to main after the task.

The current checker reports four review items and a 29/100 instruction-health score. It can generate a shared AGENTS.md and a CLAUDE.md overlay, but it keeps the conflicting Claude-only lines visible for manual review instead of silently deleting them. You can reproduce the result on the home page.

Change record

  1. Public checker launched

    Local comparison, findings, generated files, policies, and the repository-audit reservation path.

  2. Real-user measurement added

    Anonymous value-event counts, source attribution, voluntary reservations, an owner-only operations page, and a durable order ledger.

  3. Channel quality and operating workflow added

    Visit-to-result attribution by channel, daily funnel reporting, lead statuses, retention cleanup, the 18-point checklist, and this build record.

Open items

  • Google Search Console and Bing Webmaster Tools still require account-level verification.
  • Hosted payment and signed payment webhooks are not active yet; the site uses an audit-reservation form.
  • No customer testimonials or outcome claims are published because there is not enough real-user evidence yet.
  • Community distribution must be done from an identifiable human or company account, with replies tailored to the discussion.

Corrections and contact

If a checker result, product claim, or instruction-file explanation is wrong, email hello@agentsmdchecker.com. Include a minimal non-sensitive example; do not send repository secrets.