health-check

health-check is a command for Claude Code from whchoi98/project-init. It costs 19 tokens per session (1,054 once invoked), scanned D, original, MIT.

A project-audit command that checks whether a Claude Code project has its expected files, hooks, skills, permissions, and configuration.

In plain words
What is it for?
Use it to review project structure, check Git and Claude Code hooks, find available skills, and assess documentation coverage.
Why use it?
It helps reveal missing setup pieces and incorrectly configured or non-executable hooks before they cause problems.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

Part of the project-init plugin — 1 skill, 7 commands shipped together

Good fit Use it to review project structure, check Git and Claude Code hooks, find available skills, and assess documentation coverage.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/whchoi98/project-init/health-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/whchoi98/project-init

Made for: Claude Code.

Or install project-init, the plugin that ships this one along with the rest of its 1 skill, 7 commands.

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 health-check

README.md
[![agentmods](https://agentmods.dev/badge/commands/whchoi98/project-init/health-check/github.svg)](https://agentmods.dev/commands/whchoi98/project-init/health-check)
Your own site
<a href="https://agentmods.dev/commands/whchoi98/project-init/health-check"><img src="https://agentmods.dev/badge/commands/whchoi98/project-init/health-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 health-check

Your own site · 80×15
<a href="https://agentmods.dev/commands/whchoi98/project-init/health-check"><img src="https://agentmods.dev/badge/commands/whchoi98/project-init/health-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,054 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 4 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 $0.00019 $0.01054
Opus 5 $0.00010 $0.00527
Sonnet 5 $0.00004 $0.00211
Haiku 4.5 $0.00002 $0.00105

Measured 8d ago against content hash b5a6ab813ade, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade D, and why

health-check scanned grade D with 4 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 8d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

find .claude/hooks -name '*.sh' ! -perm -u+x 2>/dev/null

Reads MCP configurationmediumAgent snooping

mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.

- `.mcp.json` does not contain real tokens: +5

Enumerates other installed skillsmediumAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

find .claude/skills -name 'SKILL.md' 2>/dev/null

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

allowed-tools: Read, Glob, Grep, Bash(find:*), Bash(ls:*), Bash(git log:*), Bash(wc:*), Bash(bash -n:*), Bash(python3 -m json.tool:*)
plugins/project-init/commands/health-check.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Health Check

Validate the entire Claude Code project setup and report issues.

Step 1: Check Core Files

Verify required files exist:

ls CLAUDE.md README.md .gitignore LICENSE 2>/dev/null
ls .claude/settings.json 2>/dev/null
ls docs/architecture.md 2>/dev/null

Score:

  • CLAUDE.md exists: +20
  • .claude/settings.json exists: +10
  • docs/architecture.md exists: +10
  • README.md exists: +5
  • .gitignore exists: +5
  • LICENSE exists: +5

Step 2: Check Hook Configuration

Verify hooks are properly configured:

ls .claude/hooks/*.sh 2>/dev/null
ls .git/hooks/commit-msg 2>/dev/null

Check .claude/settings.json has hook registrations:

  • PostToolUse hook for doc-sync: +10
  • PreToolUse hook for secret scanning: +10
  • SessionStart hook: +5
  • commit-msg Git hook (Claude exclusion): +10

Verify hooks are executable:

find .claude/hooks -name '*.sh' ! -perm -u+x 2>/dev/null

Step 3: Check Skills

find .claude/skills -name 'SKILL.md' 2>/dev/null
  • code-review skill: +5
  • refactor skill: +5
  • release skill: +5
  • sync-docs skill: +5

Step 4: Check Documentation Coverage

Count module CLAUDE.md files:

find src/ app/ lib/ cmd/ -name 'CLAUDE.md' 2>/dev/null

Count source directories without CLAUDE.md:

find src/ app/ lib/ cmd/ -type d -mindepth 1 2>/dev/null
  • All modules have CLAUDE.md: +10
  • docs/decisions/ has at least one ADR: +5
  • docs/runbooks/ has at least one runbook: +5

Step 5: Check Security

  • .env is in .gitignore: +5
  • .env.example exists (if project uses env vars): +5
  • No secrets detected in CLAUDE.md or committed files: +10
  • .mcp.json does not contain real tokens: +5

Step 6: Check CLAUDE.md Quality

Run a quick quality assessment on root CLAUDE.md:

  • Under 500 lines: +5
  • Has Tech Stack section: +5
  • Has Key Commands section: +5
  • Has Project Structure section: +5
  • Commands are copy-paste ready: +5
  • No vague instructions detected: +5

Step 7: Check Tests Structure

Read the full file on GitHub · 149 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. 8d ago First seen · 149 lines · 19 tokens per session scan D b5a6ab813ade

Subscribe to this mod's changes

health-check is a command published in the GitHub repository whchoi98/project-init (2 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 1,054 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it D with 4 findings (reads agent configuration directories, reads mcp configuration, enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.