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 zorost/AI-Engineering-Lab --skill ai-output-reviewgit clone --depth 1 https://github.com/zorost/AI-Engineering-LabWrote 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/zorost/ai-engineering-lab/ai-output-review)<a href="https://agentmods.dev/skills/zorost/ai-engineering-lab/ai-output-review"><img src="https://agentmods.dev/badge/skills/zorost/ai-engineering-lab/ai-output-review/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/zorost/ai-engineering-lab/ai-output-review"><img src="https://agentmods.dev/badge/skills/zorost/ai-engineering-lab/ai-output-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00037 | $0.00962 |
| Opus 5 | $0.00018 | $0.00481 |
| Sonnet 5 | $0.00007 | $0.00192 |
| Haiku 4.5 | $0.00004 | $0.00096 |
Grade A, and why
ai-output-review 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 12d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Output Review
1 · Purpose
Make "the agent wrote it" pass the same bar as "a junior hire wrote it", read it, run it, and check it against the spec, because AI output fails in different places than human output.
2 · When to use
- Before accepting any non-trivial agent-produced diff, document, or config.
- When reviewing a teammate's PR that smells AI-generated and unreviewed.
3 · Inputs
- The spec or task statement the agent worked from.
- The diff or artifact.
- The project's verifiers: tests, linters, type checks, evals.
4 · Procedure
- Read the diff against the spec first. Ask of every changed block: which spec line does this serve? Unmotivated changes are the AI smell parade's grand marshal.
- Run the verifiers yourself. Tests, types, lint, on your machine or CI, never from the agent's claim that they passed. The agent's "all green" is a statement about its context window, not about the repo.
- Scan for secrets and egress. New endpoints, new domains, tokens in comments, telemetry you did not ask for. AI loves a helpful analytics call.
- Run the smell list. Each is innocent alone; three in one diff is a rewrite:
- Unused imports, variables, and "future-proofing" abstractions.
- Comments that narrate the code instead of the why.
- Error handling that swallows (
except: pass, empty catch). - Dependencies added for one-liners.
- Config keys that nothing reads.
- Docstrings describing a different function than the one below them.
- Check the blast radius. What runs this code, with which credentials, on what data? Match the review depth to that answer, not to the diff's size.
- Require the agent's own evidence. If the workflow produced a trace, test output, or eval score, it must be attached. No evidence, no merge.
- Decide: accept, request changes (specific, numbered), or reject. "Looks fine" after 30 seconds on 400 lines is a rejection of the review, not an acceptance of the code.
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.
- 12d ago First seen · 92 lines · 37 tokens per session scan A 5099a194dd62
ai-output-review is a skill published in the GitHub repository zorost/AI-Engineering-Lab (303 stars, last pushed 24d ago), licensed MIT. It adds 37 tokens to every session and 962 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
secure-code-review
Use this skill when reviewing or writing code that handles user input, authentication, file I/O, network requests, or database queries. Always check for common security vulnerabilities before considering the code complete.
fine-tuning-os
Use this skill when conducting a professional LLM fine-tuning engagement in Zero-Data mode via the MCP server fine-tuning-os. Triggers on: prestation de fine-tuning LLM, livraison de modèle affiné, pipeline Zero-Data, orchestration des 64 outils fine-tuning-os, cycle de vie entraînement (préparation / données…
requesting-code-review
Pre-commit review: security scan, quality gates, auto-fix.
ai-engineering-toolkit
6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
migration-review
Review database migration files when a change adds or modifies paths under migrations/. Use it before merge to collect forward, rollback, locking, and data-safety evidence.
llama-factory
Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support.