actual-mcp-server: Command for Claude Code

.claude/commands/code-health-auditor.md

code-health-auditor is a command for Claude Code from agigante80/actual-mcp-server. It costs 0 tokens per session (2,408 once invoked), scanned A, original, MIT.

A manually run command that checks the source code of actual-mcp-server for code-health problems and can create GitHub issues for genuine findings. GitHub issues are tracked work items for bugs, improvements, or other repository tasks.

In plain words
What is it for?
Running a cached or full audit, reviewing a report without creating tickets, and filing new GitHub issues for confirmed source-code findings.
Why use it?
It helps identify unused code and differences between documentation and the code, while its cache can avoid reviewing findings that were already filed.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Claude Code.

This is agigante80/actual-mcp-server's own configuration. It tells Claude Code how to work on actual-mcp-server 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 actual-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to agigante80/actual-mcp-server. 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/agigante80/actual-mcp-server/main/.claude/commands/code-health-auditor.md
Clone the repo
git clone --depth 1 https://github.com/agigante80/actual-mcp-server

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 code-health-auditor

README.md
[![agentmods](https://agentmods.dev/badge/commands/agigante80/actual-mcp-server/code-health-auditor/github.svg)](https://agentmods.dev/commands/agigante80/actual-mcp-server/code-health-auditor)
Your own site
<a href="https://agentmods.dev/commands/agigante80/actual-mcp-server/code-health-auditor"><img src="https://agentmods.dev/badge/commands/agigante80/actual-mcp-server/code-health-auditor/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 code-health-auditor

Your own site · 80×15
<a href="https://agentmods.dev/commands/agigante80/actual-mcp-server/code-health-auditor"><img src="https://agentmods.dev/badge/commands/agigante80/actual-mcp-server/code-health-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,408 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 $0.00000 $0.02408
Opus 5 $0.00000 $0.01204
Sonnet 5 $0.00000 $0.00482
Haiku 4.5 $0.00000 $0.00241

Measured 10d ago against content hash e39973056de8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

code-health-auditor 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/code-health-auditor.md · 192 lines

How it starts

The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run a source code-health audit for actual-mcp-server and create GitHub issues for genuine findings.

Usage

Accepted arguments: [--full] [--dry-run]

  • Default: cache-first. Skip findings already filed and recorded in the cache.
  • --full: ignore the cache and re-triage every finding.
  • --dry-run: print the report and the tickets that WOULD be filed, but create no tickets and write no cache. Use this for review.

This auditor is run MANUALLY on demand. It is NOT scheduled: never set up a GitHub Actions cron or a Claude Code scheduled routine for it. (Scope split: this owns SOURCE dead code and doc-to-code drift; /dep-auditor owns DEPENDENCY health. Do not re-file unused-dependency findings here.)

Provenance / canonical source

This skill is the canonical copy. The sibling project agigante80/Actual-sync#130 adopts the same code-health-auditor shape; if it diverges, reconcile against this copy. The <!-- code-health-auditor-version: 1 --> marker at the top is the drift signal: bump it when the shared logic changes, and a sibling whose marker is behind is due for a re-sync.

Project-specific values (swap these per repo; the surrounding logic stays identical):

  • Repo name in the opening line and the report (actual-mcp-server to the sibling's name).
  • The Step 2 allowlist: the @public / DEFAULT_HTTP_PORT example, src/prompts/**, src/resources/**, generated/**, and the SERVER_INFO key example are this repo's intentional-or-generated paths. The sibling lists its own.
  • The Step 3 guard names (tool_count_sync, config_drift, port_alignment, dockerfile_data_dir_alignment, compose_profile_sync, advertised_tools_sync) are this repo's committed drift guards. The sibling substitutes its own guard set.
  • The cross-reference issue (#234 here; the sibling cross-references Actual-sync#130) and any #NNN callout such as the #237 Knip-is-failing-mode note.
  • The triage label filter (gh issue list --label infrastructure), the area/priority labels, and the <!-- template-version: 3 --> issue-template marker follow each repo's conventions.

Read the full file on GitHub · 192 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 · 192 lines · 0 tokens per session scan A e39973056de8

Subscribe to this mod's changes

code-health-auditor is a command published in the GitHub repository agigante80/actual-mcp-server (53 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,408 tokens. 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.