docs: add agentchecker CLI for rule alignment

[moisesvalero]

Adds agentchecker — zero-install CLI that scans AGENTS.md, CLAUDE.md, Cursor rules, and Copilot instructions for contradictions and fixes them.

Summary by CodeRabbit

• Chores
  • Added configuration for maintaining consistency across AI coding tool instruction files, ensuring alignment of development tooling specifications and conventions.

[coderabbitai]

📝 Walkthrough

Walkthrough

A new Cursor rules prompt file rules/agent-instruction-alignment-cursorrules-prompt-file.mdc is added. It defines metadata (description, globs, alwaysApply: false) and structured instructions for keeping AGENTS.md, CLAUDE.md, Cursor rules, and Copilot instruction files synchronized, including an update workflow using npx agentchecker and a list of anti-patterns to avoid.

Changes

Agent Instruction Alignment Cursor Rule

Layer / File(s)	Summary
Agent instruction alignment rule file rules/agent-instruction-alignment-cursorrules-prompt-file.mdc	New .mdc rule file with frontmatter and full instruction set: canonical source (AGENTS.md), list of fields to keep aligned (package manager, linters, test/type tools, runtime, environment, conventions), PR update workflow with agentchecker, and anti-patterns to avoid.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

Suggested reviewers

• PatrickJS

Poem

🐇 Hop, hop, align your files in a row,
AGENTS.md leads where all the rules flow,
Cursor and Claude and Copilot too,
npx agentchecker keeps the whole crew,
No drift, no fuss — the rabbit says so! 🌿

🚥 Pre-merge checks | ✅ 3 | ❌ 2

❌ Failed checks (2 warnings)

Check name	Status	Explanation	Resolution
Title check	⚠️ Warning	The title references 'agentchecker CLI' but the actual change adds a Cursor rule file for agent instruction alignment, not documentation of the CLI itself.	Revise the title to reflect the primary change: something like 'Add Cursor rule for agent instruction alignment' or 'Add agent-instruction-alignment-cursorrules rule'.
Description check	⚠️ Warning	The description does not follow the required template structure and lacks key required information such as Contribution Type selection and Value To Cursor Users explanation.	Update the description to follow the template by selecting a contribution type checkbox, explaining the workflow value, and listing the changed files with rationale.

✅ Passed checks (3 passed)

Check name	Status	Explanation
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests

---

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

• X
• Mastodon
• Reddit
• LinkedIn

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

[coderabbitai]

Actionable comments posted: 1

🤖 Prompt for all review comments with AI agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Inline comments:
In `@rules/agent-instruction-alignment-cursorrules-prompt-file.mdc`:
- Around line 33-34: The `npx agentchecker --check-only` command in line 34
references a flag that does not exist in the agentchecker tool. Verify the
actual available CLI options for the agentchecker version being used, then
either remove the `--check-only` flag entirely or replace it with the correct
flag that provides the intended behavior (such as `--no-ai` for static-only
analysis if that matches your requirements). Update the instruction to reflect
the accurate command syntax.

🪄 Autofix (Beta)

Fix all unresolved CodeRabbit comments on this PR:

• Push a commit to this branch (recommended)
• Create a new PR with the fixes

---

ℹ️ Review info

⚙️ Run configuration

Configuration used: defaults

Review profile: CHILL

Plan: Pro

Run ID: 5230b9e5-d193-44f2-8cae-21de1f980296

📥 Commits

Reviewing files that changed from the base of the PR and between 4c11d77 and f9b843a.

📒 Files selected for processing (1)

• rules/agent-instruction-alignment-cursorrules-prompt-file.mdc

[coderabbitai]

⚠️ Potential issue | 🟡 Minor

🧩 Analysis chain

🌐 Web query:

agentchecker CLI --check-only flag support

💡 Result:

There are multiple distinct command-line interface (CLI) tools named agentchecker or agentcheck, and none of the widely documented versions explicitly support a --check-only flag [1][2][3][4][5]. Because agentchecker/agentcheck refers to different projects, you should verify which tool you are using: 1. AgentCheck (by hvardhan878 / PyPI agentcheck): This tool focuses on tracing, replaying, and asserting agent executions [4][5]. Its CLI supports commands like trace, replay, diff, assert, and show, but it does not list --check-only [4][5]. 2. AgentCheck (by Pringled): This tool scans for agent access to resources (e.g., IAM, API keys) [2]. Its CLI uses flags such as --ci and --fail-on to control behavior, but does not include --check-only [2]. 3. AgentCheck (by Eshaank08): This tool performs audits of agent instruction files [3][6]. It supports flags like --path, --interactive, --no-ai, and --json, but does not list --check-only [3][6]. 4. agentchecker (associated with cursorrules/AGENTS.md): This is a utility for scanning instruction files for contradictions [1]. Documentation for this tool is minimal and does not specify a --check-only flag [1]. If you are looking to perform a "check-only" operation, you may need to use an alternative approach specific to the tool you have installed, such as using --no-ai for static analysis only [3][6] or using assertions for CI-friendly validation [4][5].

Citations:

• 1: docs: add agentchecker CLI for rule alignment #316
• 2: https://github.com/Pringled/agentcheck
• 3: https://github.com/Eshaank08/agent-check
• 4: https://github.com/hvardhan878/agentcheck
• 5: https://pypi.org/project/agentcheck/
• 6: https://github.com/Eshaank08/agent-check/blob/main/README.md

---

Remove or correct the --check-only flag reference in line 34.

The agentchecker tool does not support a --check-only flag. Verify the actual CLI options available for the agentchecker version you're using and either remove this flag or replace it with the correct flag (e.g., --no-ai for static-only analysis, depending on your specific tool).

🤖 Prompt for AI Agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@rules/agent-instruction-alignment-cursorrules-prompt-file.mdc` around lines
33 - 34, The `npx agentchecker --check-only` command in line 34 references a
flag that does not exist in the agentchecker tool. Verify the actual available
CLI options for the agentchecker version being used, then either remove the
`--check-only` flag entirely or replace it with the correct flag that provides
the intended behavior (such as `--no-ai` for static-only analysis if that
matches your requirements). Update the instruction to reflect the accurate
command syntax.