Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/athola/claude-night-marketnpx agentmods add commands/athola/claude-night-market/ai-hygiene-auditWrote 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/athola/claude-night-market/ai-hygiene-audit)<a href="https://agentmods.dev/commands/athola/claude-night-market/ai-hygiene-audit"><img src="https://agentmods.dev/badge/commands/athola/claude-night-market/ai-hygiene-audit/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.
<a href="https://agentmods.dev/commands/athola/claude-night-market/ai-hygiene-audit"><img src="https://agentmods.dev/badge/commands/athola/claude-night-market/ai-hygiene-audit.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00028 | $0.01454 |
| Opus 5.5 | $0.00011 | $0.00582 |
| Sonnet 5.5 | $0.00006 | $0.00291 |
| Haiku 4.5 | $0.00003 | $0.00145 |
Grade A, and why
ai-hygiene-audit 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 today.
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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Hygiene Audit Command
Detect AI-specific code quality issues that traditional bloat detection misses.
When To Use
Use this command when you need to:
- Suspected AI-generated code quality issues
- Before major releases to check for hidden debt
- Reviewing PRs with suspected AI generation
- After rapid AI-assisted development sprints
When NOT To Use
- Quick fixes that don't need structured workflow
- Already know the specific issue - fix it directly
Why This Exists
AI coding creates different problems than human coding:
- 2024: First year copy > refactor in git history (GitClear)
- Tab-completion bloat: Similar code repeated instead of abstracted
- Happy path bias: Tests verify success, miss failures
- Slop: Documentation that sounds right but lacks depth
Usage
# Full AI hygiene audit
/ai-hygiene-audit
# Focus on specific area
/ai-hygiene-audit --focus git # Git history patterns
/ai-hygiene-audit --focus duplication # Tab-completion bloat
/ai-hygiene-audit --focus tests # Happy-path-only detection
/ai-hygiene-audit --focus docs # Documentation slop
/ai-hygiene-audit --focus code-debt # Code-level AI debt signals
# Generate report file
/ai-hygiene-audit --report ai-hygiene-report.md
# Set pass/fail threshold (0-100)
/ai-hygiene-audit --threshold 70
Options
| Option | Description | Default |
|---|---|---|
--focus <area> |
Limit to: git, duplication, tests, docs, deps, code-debt |
all |
--report <file> |
Save detailed report to file | stdout |
--threshold <score> |
Fail if hygiene score below threshold | none |
--json |
Output structured JSON for CI integration | false |
What It Detects
Git History Patterns
- Massive single commits: 500+ line additions (vibe coding signature)
- Refactoring deficit: <5% of commits involve refactoring
- Churn spikes: Code revised within 2 weeks of creation
Duplication (Tab-Completion Bloat)
- Repeated blocks: 5+ line duplicates across files
- Suffix variants: names that differ only by
_v2,_newor_old, outside test modules - Copy-paste patterns: Same logic with minor variations
- Competing implementations: One function name with different bodies in two or more files, listed in the same report
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.
- today Changed · +3 lines d37198306c2d
- 1mo ago First seen · 168 lines · 28 tokens per session scan A 545f71746f41
ai-hygiene-audit is a command published in the GitHub repository athola/claude-night-market (343 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 1,454 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.
Other commands, from other repositories
prism-graph
Export Prism's graph of this repository and summarise it.
hotfix
Ship a fast branch-based P0 hotfix — diagnose, implement, open a ready-for-review PR, then verify + review after (deferred by design).
sc-adversarial-hunt
General-purpose adversarial analysis with competing finder, skeptic, and arbiter agents. Works on code, plans, docs, configs, or any artifact.
bmad-review-edge-case-hunter
Walk every branching path and boundary condition in content, report only unhandled edge cases. Orthogonal to adversarial review - method-driven not attitude-driven. Use when you need exhaustive edge-case analysis of code, specs, or diffs.
cg-senior-code-review
Perform deep, findings-first senior engineering code reviews of any change in any language or stack. Use when reviewing a phase, feature branch, pull request, commit, or uncommitted changes for correctness bugs, security and abuse risks, regressions to existing behavior, concurrency and lifecycle defects, performance…
lint:explain
(Ruff) Explain a ruff error and show the PROPER solution (without noqa!).