conventions-check

conventions-check is a command for Claude Code from eugenelim/agent-ready-repo. It costs 28 tokens per session (594 once invoked), scanned A, original, Apache-2.0.

A command that checks project instruction files and coding-agent components—such as skills, subagents, and commands—against documented repository conventions.

In plain words
What is it for?
Checking file lengths, symlinks or matching copies, required folders, YAML metadata, naming, stray files, and broken internal links.
Why use it?
It finds structural and documentation problems without changing files automatically. This helps keep agent instructions consistent, linked correctly, and easy to maintain.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md; mentions subagents; mentions AGENTS.md.

Good fit Checking file lengths, symlinks or matching copies, required folders, YAML metadata, naming, stray files, and broken internal links.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/eugenelim/agent-ready-repo/conventions-check
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/eugenelim/agent-ready-repo

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for conventions-check

README.md
[![agentmods](https://agentmods.dev/badge/commands/eugenelim/agent-ready-repo/conventions-check/github.svg)](https://agentmods.dev/commands/eugenelim/agent-ready-repo/conventions-check)
Your own site
<a href="https://agentmods.dev/commands/eugenelim/agent-ready-repo/conventions-check"><img src="https://agentmods.dev/badge/commands/eugenelim/agent-ready-repo/conventions-check/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for conventions-check

Your own site · 80×15
<a href="https://agentmods.dev/commands/eugenelim/agent-ready-repo/conventions-check"><img src="https://agentmods.dev/badge/commands/eugenelim/agent-ready-repo/conventions-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 594 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00028 $0.00594
Opus 5 $0.00014 $0.00297
Sonnet 5 $0.00006 $0.00119
Haiku 4.5 $0.00003 $0.00059

Measured 10d ago against content hash 7455d6ae51bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

conventions-check scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/conventions-check.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify the conventions below and report findings. If your project ships linters that cover any of these, run them; otherwise inspect the files directly and report each check by hand. Don't auto-fix — report findings and let the user decide.

AGENTS.md hygiene

  1. Root AGENTS.md is under 120 lines; a core seed is under 100 lines.
  2. CLAUDE.md is a symlink to AGENTS.md, or a byte-identical copy of it. (Native Windows checkouts can't materialise symlinks without elevation, so an identical regular file is accepted; a diverged regular file is not.)
  3. Scoped or local instruction files are under 80 lines; _example skeletons are under 35.
  4. Internal links resolve.
  5. docs/CHARTER.md and the Diátaxis guide subdirectories exist.

Agent-artifact hygiene (skills, subagents, commands)

  1. Every skill, subagent, and command has well-formed YAML frontmatter with the required keys (name, description).
  2. Skill directory names match the frontmatter name; subagent and command filenames match their name; all kebab-case.
  3. Frontmatter carries no unknown keys.
  4. Each skill dir contains a SKILL.md and no stray .md siblings.
  5. Internal markdown links inside each artifact resolve.

Credentialed-skill rules

Scoped to skills whose SKILL.md declares metadata.credentialed: true (project-specific fields live under metadata: per the agentskills.io spec):

  1. The body contains a ### Security rules (non-negotiable) heading and the three required security substrings inside that section (the verbatim "Don't" block).
  2. For metadata.primitive-class: credentialed-cli: no script under the skill's scripts/ directory accepts an argparse flag whose normalised name (strip leading -, casefold, -_) is one of {token, api_token, api_key, bearer, pat, password}. This covers literal strings and "--" + "name"-style concatenation.
  3. No script under a credentialed skill's scripts/ directory contains the substring .agentbundle/credentials.env unless the opt-out comment # credentialed-primitive: reads-creds-directly appears on the same line.

Read the full file on GitHub · 49 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 49 lines · 28 tokens per session scan A 7455d6ae51bc

Subscribe to this mod's changes

conventions-check is a command published in the GitHub repository eugenelim/agent-ready-repo (20 stars, last pushed today), licensed Apache-2.0. It adds 28 tokens to every session and 594 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.