Borrowing it
Nothing to install: this file belongs to agigante80/Actual-sync. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/agigante80/Actual-sync/main/.claude/commands/code-health-auditor.mdgit clone --depth 1 https://github.com/agigante80/Actual-syncWrote 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.
[](https://agentmods.dev/commands/agigante80/actual-sync/code-health-auditor)<a href="https://agentmods.dev/commands/agigante80/actual-sync/code-health-auditor"><img src="https://agentmods.dev/badge/commands/agigante80/actual-sync/code-health-auditor.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.02124 |
| Opus 5 | $0.00000 | $0.01062 |
| Sonnet 5 | $0.00000 | $0.00425 |
| Haiku 4.5 | $0.00000 | $0.00212 |
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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 178 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-sync 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
The canonical copy of this skill lives in the sibling project
agigante80/actual-mcp-server (.claude/commands/code-health-auditor.md). This repo adopts
the same shape under agigante80/Actual-sync#130; if the two diverge, reconcile against the
sibling. Both carry <!-- code-health-auditor-version: 1 --> so divergence is detectable.
Keep project-specific values (paths, labels, guard/script names) minimal so the two stay
alignable; the auditing logic below must stay identical to the canonical.
Overview
One pass: read the cache, run Knip (dead code) with the committed config, run the drift guards, triage findings against the documented allowlist, then open gate-ready tickets for the genuine ones and update the cache. Never auto-remove code or auto-edit docs: file tickets only. Output uses no em or en dashes.
Step 1 - Read the cache
Read docs/audit/deadcode-audit-cache.json if it exists. Schema:
{
"lastFullAudit": "<ISO timestamp>",
"findings": {
"<kind:path:symbol>": {
"firstSeen": "<YYYY-MM-DD>",
"lastSeen": "<YYYY-MM-DD>",
"status": "filed|allowlisted|wontfix",
"ticket": "<#NNN or null>",
"notes": "<short reason>"
}
}
}
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.
- 2d ago First seen · 178 lines · 0 tokens per session scan A 63c44eb57722
code-health-auditor is a command published in the GitHub repository agigante80/Actual-sync (12 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,124 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 2026-09-04.
Other commands, from other repositories
perf-profile.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
ui-snapshot.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
crisis
A crisis-response procedure for software incidents such as an outage, a stopped bot, a critical bug, or a changed external dependency. It is written in Korean.
deep-audit.skeleton
Aciklama: Bu bolum Bootstrap tarafindan manifest verileriyle doldurulur. Gerekli manifest alanlari: project.description, stack.primary, project.structure, project.subprojects, stack.orm, stack.authmethod Ornek cikti.
fix-issues
Pick up one approved task, implement the fix, and close it.
security-audit
Full security review — GitHub alerts, static code analysis, live app check — then a task per finding.