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 skills/wolfenazz/yzpzcode/critique-theaternpx skills add wolfenazz/YzPzCode --skill critique-theatergit clone --depth 1 https://github.com/wolfenazz/YzPzCodeWrote 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/wolfenazz/yzpzcode/critique-theater)<a href="https://agentmods.dev/skills/wolfenazz/yzpzcode/critique-theater"><img src="https://agentmods.dev/badge/skills/wolfenazz/yzpzcode/critique-theater.svg" alt="Measured on agentmods" 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 | $0.00022 | $0.00414 |
| Opus 5 | $0.00011 | $0.00207 |
| Sonnet 5 | $0.00004 | $0.00083 |
| Haiku 4.5 | $0.00002 | $0.00041 |
Grade A, and why
critique-theater 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.
This is a copy
100% identical to critique-theater — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Critique theater
The atom that keeps the devloop honest. After each generation pass,
the agent self-critiques along five dimensions (clarity, hierarchy,
typography, motion, brand consistency — the panel is configurable per
plugin) and emits a critique.score signal in the 0-5 range. The
score is the variable a stage's until expression can read:
{
"id": "critique",
"atoms": ["critique-theater"],
"repeat": true,
"until": "critique.score >= 4 || iterations >= 3"
}
Output shape
The agent writes the critique panel to critique.json in the project
cwd plus a structured event the daemon's pipeline runner reads:
{
"kind": "critique-panel",
"score": 4,
"axes": {
"clarity": { "score": 4, "notes": "..." },
"hierarchy": { "score": 4, "notes": "..." },
"typography": { "score": 5, "notes": "..." },
"motion": { "score": 3, "notes": "needs easing pass" },
"brand": { "score": 4, "notes": "..." }
}
}
Convergence + escape hatches
- Critique converges at
score >= 4per defaultuntil. - Iteration cap (
OD_MAX_DEVLOOP_ITERATIONS, default 10) always wins even when the score never reaches 4. - The user can break out via
od ui respondwith actionbreak-loopor the desktop "Stop refining" button.
What ships with it
1 file 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.
- yesterday First seen · 52 lines · 22 tokens per session scan A 0e90ea437ba7
critique-theater is a skill published in the GitHub repository wolfenazz/YzPzCode (13 stars, last pushed today), licensed Apache-2.0. It adds 22 tokens to every session and 414 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to critique-theater, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
golden-rss
Use when testing the rss golden build.
android-pentest
安卓应用渗透测试 — APK分析、Hook、自动化测试、运行态驱动、签名恢复、抓包分析.
tui-migrate-setup
Migrates the supported subset of an existing Warp GUI setup into Warp Agent CLI without exposing credentials or application state. Use in Warp Agent CLI when a user wants to copy or move compatible settings or global file-based MCP servers from the desktop app, set up Warp Agent CLI from an existing GUI installation…
alive:system-upgrade
Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.
bib-coverage
Compare a project .bib against a Paperpile project/topic folder to find uncited papers or unfiled entries. Use when the user asks to compare a project .bib against a Paperpile project/topic folder to find uncited papers or unfiled entries.