replicant-mcp: Command for Claude Code

.claude/commands/health-report.md

health-report is a command for Claude Code from thecombatwombat/replicant-mcp. It costs 7 tokens per session (466 once invoked), scanned A, original, MIT.

A command that creates a dashboard about a codebase's health by checking complexity, file sizes, type-safety patterns, shared mutable state, test coverage, and the largest files and functions.

In plain words
What is it for?
Use it to review a project's maintainability, find oversized or complex code, assess testing levels, and identify risky TypeScript patterns.
Why use it?
It turns several maintenance checks into one consistent report. This makes structural problems and areas needing refactoring easier to spot.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is thecombatwombat/replicant-mcp's own configuration. It tells Claude Code how to work on replicant-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything replicant-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to thecombatwombat/replicant-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/thecombatwombat/replicant-mcp/master/.claude/commands/health-report.md
Clone the repo
git clone --depth 1 https://github.com/thecombatwombat/replicant-mcp

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 health-report

README.md
[![agentmods](https://agentmods.dev/badge/commands/thecombatwombat/replicant-mcp/health-report/github.svg)](https://agentmods.dev/commands/thecombatwombat/replicant-mcp/health-report)
Your own site
<a href="https://agentmods.dev/commands/thecombatwombat/replicant-mcp/health-report"><img src="https://agentmods.dev/badge/commands/thecombatwombat/replicant-mcp/health-report/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-report

Your own site · 80×15
<a href="https://agentmods.dev/commands/thecombatwombat/replicant-mcp/health-report"><img src="https://agentmods.dev/badge/commands/thecombatwombat/replicant-mcp/health-report.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 466 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 $0.00007 $0.00466
Opus 5 $0.00003 $0.00233
Sonnet 5 $0.00001 $0.00093
Haiku 4.5 $0.00001 $0.00047

Measured 10d ago against content hash c6f2948ff666, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

health-report 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/health-report.md · 43 lines

What it actually says

Generate a comprehensive codebase health report by running these checks:

  1. Complexity violations: Run scripts/check-complexity.sh and capture output
  2. Module sizes: Count files and lines per module (src/tools/, src/services/, src/adapters/, src/types/, src/parsers/, src/utils/)
  3. Type safety: Count occurrences of as any, as unknown, Record<string, unknown> return types, and [key: string]: unknown in src/
  4. Global mutable state: Search for let at module level in src/ (not inside functions/classes)
  5. Test ratio: Count total lines in src/ and tests/, calculate test-to-source ratio
  6. Top 5 largest files: List the 5 largest .ts files in src/ by line count
  7. Top 5 largest functions: Use the complexity script output or manual search

Present results as a markdown table dashboard:

## Codebase Health Report

| Dimension | Rating | Details |
|-----------|--------|---------|
| Module boundaries | ... | ... |
| File sizes | ... | ... |
| Test coverage | ... | ... |
| Type safety | ... | ... |
| Complexity hotspots | ... | ... |
| Global state | ... | ... |

### Top 5 Largest Files
| File | Lines |
|------|-------|
| ... | ... |

### Violations
(list from check-complexity.sh, or "None")

Rate each dimension as Excellent / Good / Fair / Needs Work based on:

  • File sizes: Excellent if all <200, Good if all <300, Fair if 1-2 over, Needs Work if 3+
  • Type safety: Excellent if 0 unsafe casts, Good if <3, Fair if <10, Needs Work if 10+
  • Test ratio: Excellent if >0.8, Good if >0.5, Fair if >0.3, Needs Work if <0.3
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 · 43 lines · 7 tokens per session scan A c6f2948ff666

Subscribe to this mod's changes

health-report is a command published in the GitHub repository thecombatwombat/replicant-mcp (16 stars, last pushed 1mo ago), licensed MIT. It adds 7 tokens to every session and 466 once invoked, about $0.0000 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.