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.
npx skills add jmagly/aiwg --skill cleanup-auditgit clone --depth 1 https://github.com/jmagly/aiwgWrote 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/skills/jmagly/aiwg/cleanup-audit)<a href="https://agentmods.dev/skills/jmagly/aiwg/cleanup-audit"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/cleanup-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/skills/jmagly/aiwg/cleanup-audit"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/cleanup-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 69 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00021 | $0.02991 |
| Opus 5.5 | $0.00008 | $0.01196 |
| Sonnet 5.5 | $0.00004 | $0.00598 |
| Haiku 4.5 | $0.00002 | $0.00299 |
Grade A, and why
cleanup-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 1mo 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 — 367 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cleanup Audit
Audits the codebase for accumulated dead weight: unused TypeScript/JS exports, orphaned source files, npm dependencies that are declared but never imported, and manifest entries that point to files that do not exist. Every finding carries a confidence rating. Only HIGH confidence findings are safe to auto-fix.
Natural Language Triggers
Users may say:
- "cleanup audit"
- "dead code audit"
- "find dead code"
- "orphan files"
- "unused exports"
- "cleanup analysis"
- "find unused dependencies"
- "stale manifest entries"
- "what can I delete"
- "codebase cleanup"
Parameters
--scope <path>
Restrict analysis to a subtree. Default is the full repository root.
aiwg cleanup-audit --scope src/cli/
aiwg cleanup-audit --scope agentic/code/addons/
--type <exports|files|deps|manifests>
Run only the specified audit type. Omit to run all four.
| Value | Audits |
|---|---|
exports |
TypeScript/JS exports with no importers |
files |
Source files not referenced by any import or manifest |
deps |
npm dependencies declared in package.json but not used in code |
manifests |
Manifest entries (skills, agents) whose source file does not exist |
Multiple types can be combined:
aiwg cleanup-audit --type exports --type deps
--json
Emit findings as newline-delimited JSON to stdout instead of the formatted report. Useful for piping into other tools or CI scripts.
aiwg cleanup-audit --json | jq 'select(.confidence == "HIGH")'
--fix
Auto-apply removals for all HIGH confidence findings. Has no effect without confirmation when any HIGH finding involves a non-trivial deletion (more than 10 lines or a full file). Combine with --dry-run to preview what --fix would remove.
--dry-run
Show what --fix would remove without writing any changes. If used without --fix, behaves as the default read-only audit.
Execution Flow
Phase 1: Determine Analysis Scope
- Parse
--scope— default to repo root - Parse
--type— default to all four types - Parse
--json,--fix,--dry-runflags - Build file inventory for the scope:
- All
.ts,.tsx,.js,.mjsfiles (for exports and files audits) package.json(for deps audit)- All
manifest.jsonfiles underagentic/(for manifests audit)
- All
- Communicate scope before analysis begins
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.
- 1mo ago First seen · 367 lines · 21 tokens per session scan A 2b46e84fecd9
cleanup-audit is a skill published in the GitHub repository jmagly/aiwg (225 stars, last pushed today), licensed MIT. It adds 21 tokens to every session and 2,991 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 skills, from other repositories
attest
Verifying spec compliance: extracts ACs from specs, adversarially checks conformance, generates BDD scenarios and traceability matrices. Use when impl must be proven to match a PRD/SRS/AC.
guardian
Gatekeeping Git/PR by classifying change essence and recommending granularity, naming, and strategy; the ship recipe also executes PR delivery (create, CI watch, merge, cleanup) with Ask First on merge. Use when PR preparation, commit strategy, or gated PR delivery is needed.
atlas
Analyzing dependencies, circular references, and God Classes; authoring ADRs/RFCs. Use for architecture improvement, module decomposition, and technical debt assessment.
judge
Reviewing code via multi-engine orchestration (Claude + Codex) on three axes — secure, correct, and lean — shipping only findings worth fixing. Use for PR review or pre-commit. Complements Zen.
quill
Adding JSDoc/TSDoc, updating READMEs, replacing any types with proper definitions, and adding high-value comments to complex logic. Use for documentation gaps or type safety.
zen
Refactoring code: variable naming, function extraction, magic number constants, dead code removal. Does not change behavior. Not for bugs (Judge), security (Sentinel), tests (Radar), or features (Builder).