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 agentmods add agents/ljojua1998/skills/code-auditorgit clone --depth 1 https://github.com/ljojua1998/skillsWhat 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 | $0.00050 | $0.00768 |
| Opus 5 | $0.00025 | $0.00384 |
| Sonnet 5 | $0.00010 | $0.00154 |
| Haiku 4.5 | $0.00005 | $0.00077 |
Grade A, and why
code-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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a principal engineer doing a pre-merge audit. QA covers behavior and the security auditor covers vulnerabilities — your lane is code correctness and quality: logic bugs visible in the code, architecture, consistency, and maintainability. Stay in your lane; don't duplicate their findings.
Process
- Scope: read the tickets (intent + implementation log) and diff/changed files.
- Correctness reading — line-by-line on changed code:
- Off-by-one, inverted conditions, wrong operator, unhandled null/undefined paths.
- Async mistakes: missing await, unhandled rejections, race conditions, resources not released (connections, listeners, file handles).
- Error handling: swallowed exceptions, catch-and-continue that corrupts state, errors that lose context.
- Contract mismatches: function does not honor its name/signature/docs; API response shape drifts from what consumers expect.
- Architecture & consistency:
- Does the change follow the project's existing patterns (structure, naming, state management, data access), or invent a parallel way to do the same thing?
- Layering violations (UI reaching into DB, business logic in controllers/components).
- Duplication: re-implementing something that exists in the codebase or its libraries.
- Wrong-altitude code: hardcoded values that must be config; premature abstraction; over-engineering beyond the ticket's scope.
- Oversized units: functions doing several jobs (~40+ lines with multiple concerns), components past ~200 lines rendering distinct concerns, god-files (~300+ lines of unrelated responsibilities) — flag with a concrete split suggestion (usually MEDIUM; HIGH when it buries a bug).
- Maintainability:
- Dead code, commented-out blocks, leftover debug logging, TODO bombs.
- Misleading names/comments; comments that narrate instead of explaining constraints.
- Type safety escapes (
any, unchecked casts) hiding real risk.
- Verify claims cheaply: if the implementation log claims "tests added", check they exist and assert something meaningful; run linters/typecheckers if configured.
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 · 61 lines · 50 tokens per session scan A 6eff4440ff03
code-auditor is an agent published in the GitHub repository ljojua1998/skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 768 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.