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 lucastamoios/skills --skill critiquegit clone --depth 1 https://github.com/lucastamoios/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/lucastamoios/skills/critique)<a href="https://agentmods.dev/skills/lucastamoios/skills/critique"><img src="https://agentmods.dev/badge/skills/lucastamoios/skills/critique/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/lucastamoios/skills/critique"><img src="https://agentmods.dev/badge/skills/lucastamoios/skills/critique.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 | $0.00061 | $0.00808 |
| Opus 5.5 | $0.00024 | $0.00323 |
| Sonnet 5.5 | $0.00012 | $0.00162 |
| Haiku 4.5 | $0.00006 | $0.00081 |
Grade A, and why
critique 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 4d 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 — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Critique
Replace the expert's manual back-and-forth ("better hook", "more visceral", "change these words") with a judgment that a script revision can act on. The expert's experience: the model knows the rules but does not follow them, so this skill checks each rule against the actual lines.
Contract
Follow the marketing contract. Input schema: critique.input. Output schema: critique.output. Output JSON only.
Method
- Load the built-in criteria, including its calibration examples. Criteria in
input.criteriawith the sameidreplace the built-in ones; new ids are added. - Check every claim and every spoken example against the text of
material(andcreator.authority,creator.brand), not against the source the script declares. A claim sourced only fromoffer,angleor another skill's output failsclaims_sourced. A spoken example that is not inmaterialfailsclaims_sourcedeven whenpreparationcalls it a demo. 2b. Score each criterion 0 (fails), 1 (partly), or 2 (meets), quoting the line or beat asevidence. Do not score from the angle or intentions; score what is written. Do not score length. Count the spoken words yourself (about 2.5 per second) and report the count and seconds inwarnings, compared with the reference duration whenreference_analysisgives one and with the calibration examples in the criteria. A script is never better for being shorter. - For each failure, write an issue anchored to a
beat_idwith a concretefix: a replacement line, a new visual, or a cut. "Make it more engaging" is not a fix. A fix never introduces a fact, number, date or example that is not inmaterial; when one is needed, the fix is a question to the creator. - Severity:
blockerwhen the viewer would scroll away or be misled (no promise in the hook, unsourced claim stated as fact, nothing to show);majorwhen the expert would ask for a change;minorfor polish. - List in
keepwhat works, so the revision does not break it. - Verdict:
approve: no blocker or major issue.revise: fixable by rewriting lines and visuals.rethink: the problem is upstream: the material is an opinion with no case, the angle has no so-what, or the reference mechanism cannot be executed with the creator's assets. Say which step inrethink_reason.
- Write
rewrite_briefas direct instructions to marketing:script in revise mode, ordered by impact. 7b. When every blocker and major fix needs a fact only the creator can give (an outcome, a real example, how the thesis connects), returnstatus: "needs_input"with the exact questions inmissing_inputs, quoting his words. Keep the fullresult(scores, issues, verdict) for the record. Another script round without the fact only produces placeholders. - If
roundequalsmax_roundsand the verdict would still berevise, return the verdict anyway and add a warning that a human should decide.
What ships with it
2 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.
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.
- 4d ago Changed · +2 lines da0b698bcd38
- 11d ago First seen · 29 lines · 61 tokens per session scan A 107c2fa39cce
critique is a skill published in the GitHub repository lucastamoios/skills (0 stars, last pushed 5d ago), licensed MIT. It adds 61 tokens to every session and 808 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 2026-11-05.
critique compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| critiquelucastamoios/skills | Skill | 0 | 5d ago | MIT | A | 61 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 135k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 100k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 395k | today | MIT | A | 36 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 80k | 9d ago | MIT | A | 200 | Claude Code, Codex |
| next-cache-components-adoptionvercel/next.js | Skill | 144k | today | MIT | A | 95 | Claude Code |
| chat-pet-sprite-creationmicrosoft/vscode | Skill | 195k | today | MIT | A | 53 | Claude Code, Codex |