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.
git clone --depth 1 https://github.com/ooiyeefei/cccWrote 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/commands/ooiyeefei/ccc/critique-survey)<a href="https://agentmods.dev/commands/ooiyeefei/ccc/critique-survey"><img src="https://agentmods.dev/badge/commands/ooiyeefei/ccc/critique-survey.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 5.1 | $0.00026 | $0.01368 |
| Opus 5 | $0.00013 | $0.00684 |
| Sonnet 5 | $0.00005 | $0.00274 |
| Haiku 4.5 | $0.00003 | $0.00137 |
Grade A, and why
critique-survey 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 7d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Critique Survey
Take an existing survey (pasted text, URL, or file) and return a Jarrett-style review with:
- A punch-list of issues (severity-ranked)
- Concrete rewrites for the worst 3–5
- A verdict on the overall instrument
Usage
/critique-survey
The user will paste, link, or attach. If they paste a URL, fetch it (WebFetch). If a file path, read it. If they paste text directly, work from that.
Process
Always invoke the rethink-surveys skill first.
Step 1 — Catalog the questions
Read every question. Number them. For each, capture:
- The question text (verbatim)
- Answer format (open / single / multi / scale / etc.)
- Position in flow (early / mid / late)
- Any branching shown
- Any consent or contact treatment
If the survey is long (>15 Qs), summarize structurally before diving in.
Step 2 — Apply the seven principles
For each question, check against:
- Past behavior, not hypotheticals. Flag any "Would you..." / "Will you..." / "Do you think..."
- No pre-signaling the right answer. Flag "Most people..." / loaded adjectives in option labels / leading question stems.
- Open-ended before narrowing. Is there at least one open question early? Is it forced into a checkbox structure?
- Screening / diagnosis / segmentation separation. Are demographic questions polluting the diagnostic flow?
- No double-barreled questions. Flag any "X and Y?" question.
- Behavioral anchors over Likert. Flag any 1-5/1-7 with vague anchors ("strongly agree"). Suggest behavioral replacements where possible.
- Honest length claim. If a length is stated, estimate the actual time and flag mismatch.
Step 3 — Apply the 4-part structural check
Tag each Q with which part it serves: discovery / diagnostic / intent / segmentation. Then check:
- Discovery missing? Survey is checkbox-only — won't capture novelty. Recommend adding one open Q at start.
- Diagnostic missing or shallow? Won't be analyzable across users — recommend adding severity/frequency.
- Intent missing? Won't surface demand signal. Recommend adding WTP buckets or top-3 priority.
- Segmentation missing? Won't enable cohorting. Recommend at minimum a single respondent-type Q.
- Same part hit by 3+ questions? Survey is bloated in one direction. Recommend cuts.
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.
- 7d ago First seen · 169 lines · 26 tokens per session scan A 30b705e12971
critique-survey is a command published in the GitHub repository ooiyeefei/ccc (485 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 1,368 once invoked, about $0.0001 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.