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 simota/agent-skills --skill judgegit clone --depth 1 https://github.com/simota/agent-skillsWrote 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/simota/agent-skills/judge)<a href="https://agentmods.dev/skills/simota/agent-skills/judge"><img src="https://agentmods.dev/badge/skills/simota/agent-skills/judge/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/simota/agent-skills/judge"><img src="https://agentmods.dev/badge/skills/simota/agent-skills/judge.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 | $0.00046 | $0.05873 |
| Opus 5.5 | $0.00018 | $0.02349 |
| Sonnet 5.5 | $0.00009 | $0.01175 |
| Haiku 4.5 | $0.00005 | $0.00587 |
Grade A, and why
judge 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 — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Judge
"Good code needs no defense. Bad code has no excuse."
Code review specialist delivering verdicts on three quality axes — secure · correct · lean — plus intent alignment, via tri-engine parallel review (Codex + Antigravity + Claude Code subagents) with grounding verification. A pair mode (pair) improves code conversationally, one finding at a time.
What ships with it
24 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- _common 10 B
- reference/_common 13 B
- reference/ai-code-scrutiny.md 5.2 KB
- reference/antigravity-review-usage.md 7.6 KB
- reference/autorun-schema.md 1.6 KB
- reference/boundaries.md 2.7 KB
- reference/claude-review-usage.md 23 KB
- reference/code-smell-detection.md 5.6 KB
- reference/codex-integration.md 7.7 KB
- reference/codex-review-usage.md 16 KB
- reference/collaboration-patterns.md 7.4 KB
- reference/consistency-patterns.md 4.9 KB
- reference/fix-prompt-generation.md 12 KB
- reference/framework-reviews.md 4.6 KB
- reference/lean-review.md 7.1 KB
- reference/pair-review.md 6.3 KB
- reference/recipes-detail.md 6.6 KB
- reference/research-citations.md 9.4 KB
- reference/review-anti-patterns.md 5.0 KB
- reference/review-effectiveness.md 7.0 KB
- reference/skill-review-criteria.md 6.0 KB
- reference/test-quality-patterns.md 8.9 KB
- reference/tri-engine-review.md 15 KB
- reference/zen 9 B
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 Changed d1b71c87e43e
- 13d ago Changed c535d40992bf
- 18d ago Changed f60c32821710
- 1mo ago Changed · -2 lines d9d4f39ae8b6
- 1mo ago Changed · -1 lines 51adabfbe329
- 1mo ago First seen · 267 lines · 46 tokens per session scan A ee02be9501ba
judge is a skill published in the GitHub repository simota/agent-skills (96 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 5,873 once invoked, about $0.0002 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
discount-review
Inspect the discount policy fixture with a repeatable review checklist and helper script.
code-review
Reviews code for bugs, security issues, and best practices.
cleanup-audit
Audit codebase for dead code, unused exports, orphaned files, and stale manifests.
deep-review
Parallel competency-based code review. Launches independent Agent reviewers per competency (security, performance, architecture, database, concurrency, error-handling, frontend, testing), each with a focused checklist and isolated context. Synthesizes findings into unified report with FIX/DEFER/ACCEPT triage. Use…
link-check
Verify @file references in AIWG skills and agents against the linking contract — per-file or corpus-wide, with optional auto-fix.
architecture-quality
Keep web applications, APIs and services readable as they grow: choose feature or domain seams, assign state ownership, enforce dependency direction, keep adapters thin, and verify file shape. Use when starting or extending a web app, backend, frontend, API or multi-page product; when a change makes a module hard to…