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 rikdc/ai-skills --skill review-evalsgit clone --depth 1 https://github.com/rikdc/ai-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/rikdc/ai-skills/review-evals)<a href="https://agentmods.dev/skills/rikdc/ai-skills/review-evals"><img src="https://agentmods.dev/badge/skills/rikdc/ai-skills/review-evals/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/rikdc/ai-skills/review-evals"><img src="https://agentmods.dev/badge/skills/rikdc/ai-skills/review-evals.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 | $0.00103 | $0.01250 |
| Opus 5.5 | $0.00041 | $0.00500 |
| Sonnet 5.5 | $0.00021 | $0.00250 |
| Haiku 4.5 | $0.00010 | $0.00125 |
Grade A, and why
review-evals 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 yesterday.
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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Evals - judgement over evals and skills
Reviews the parts of a skill or eval that a script cannot decide. The
deterministic gate (tests/test-evals.sh, run by make test and in CI)
already covers layout, rubric arithmetic, fixture hygiene, manifests and
frontmatter conventions. Never spend judgement on what that gate decides:
run it first and read its findings.
Nothing here runs in CI. A review needs a model, so it runs on a contributor's machine, and it only ever reads refs you trust.
Scope the review
- An eval run left pending criteria:
--result <dir>(see "Grade a run"). - A pull request:
gh pr diff <number>plustests/test-evals.sh --changes <base-ref>to list the skills and scenarios it touches. - A working branch:
tests/test-evals.sh --changes origin/main.
Judge a scenario
Read task.md, criteria.json, inputs/setup.sh, the scenario's optional
checks.sh, and the unit (SKILL.md or command) the scenario claims to
exercise. Then ask, in this order:
- Does it discriminate? Name the run that scores well without the unit's
guidance. If none exists - the task states the answer, or a criterion holds
for any outcome (
git log -1, an artifact the task hands over) - the scenario proves nothing. This is the failure that matters most. - Can a correct run pass every criterion? Look for a rubric item the task's own end state contradicts: a clean working tree when the task asks for an untracked artifact, a heading the final step moves, a file the fixture never creates.
- Is every criterion documented by the unit? Grade only behaviour the unit states. If the behaviour is worth testing but undocumented, put it in the task instead of the rubric.
- Does the task leak the process? If the task spells out the unit's own procedure step by step, an agent without the unit passes. Keep intent in the task; leave the process to the unit.
- Is the shim faithful? A recording shim must parse like the real tool -
long and short flags,
--flag=value,-for stdin, values that begin with-- and record what the tool would infer, not only what it receives. - Is the fixture honest? Deterministic, prompt-free, executable, no network, writes only inside the sandbox, and no checked-in file the script overwrites.
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.
- yesterday First seen · 98 lines · 103 tokens per session scan A 96541dace319
review-evals is a skill published in the GitHub repository rikdc/ai-skills (2 stars, last pushed 2d ago), licensed MPL-2.0. It adds 103 tokens to every session and 1,250 once invoked, about $0.0004 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 2026-10-18.
Other skills, from other repositories
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
bug-fixer
A bug reproduces, the expected behaviour is clear, and the fix stands apart from the current work.
api-testing
HTTP API testing for TypeScript (Supertest) and Python (httpx, pytest). Test REST APIs, GraphQL, request/response validation, authentication, and error handling.
bun-jest-migration
Use when migrating from Jest to Bun's test runner, import compatibility, mocks, and config.
bun-test-mocking
Use for mock functions in Bun tests, spyOn, mock.module, implementations, and test doubles.