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 commands/ooiyeefei/ccc/design-surveygit 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/design-survey)<a href="https://agentmods.dev/commands/ooiyeefei/ccc/design-survey"><img src="https://agentmods.dev/badge/commands/ooiyeefei/ccc/design-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 | $0.00021 | $0.01415 |
| Opus 5 | $0.00010 | $0.00707 |
| Sonnet 5 | $0.00004 | $0.00283 |
| Haiku 4.5 | $0.00002 | $0.00142 |
Grade A, and why
design-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 6d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Survey
Walk the user through designing a new survey, end to end. Output is a finalized question set + output schema, ready to hand off to /turn-into-app.
Usage
/design-survey
Optionally with a use-case hint:
/design-survey for a startup founder doing customer discovery
/design-survey for an event we're running next month
/design-survey for our gig-worker retention diagnosis
Process
Always invoke the rethink-surveys skill first. Then walk the user through these steps in order, asking ONE question per turn. Don't dump the whole flow at once.
Step 1 — Research goal (mandatory)
Ask: "In one sentence, what's the research goal? Pretend you're explaining to a busy stakeholder why this survey is worth doing."
If the user gives a vague answer ("to understand users"), push back: "Specifically — what decision will the survey help you make? If 100 responses came in tomorrow, what would change?"
Don't proceed without a sharp goal.
Step 2 — Audience
Ask: "Who's the respondent, and how will they encounter the survey? (e.g., QR code at venue, email to warm list, push from in-app)"
The answer determines the modality default:
- QR / cold → form, ≤60s
- Email / warm → form + voice, ≤90s
- In-app / engaged → AI-interviewer mode possible
Step 3 — Length budget
Ask: "What's an honest length budget? 60 / 90 / 180 seconds, or longer?"
Reference Jarrett's rule: never lie about length on the landing page. If they say 60s, they need a 60s instrument.
Step 4 — Hypotheses
Ask: "What 2–4 things are you trying to prove or disprove? Each becomes a section of the survey."
If they don't have hypotheses → suggest reading references/use-cases.md for templates with pre-formed hypotheses they can fork.
Step 5 — Match to template (if applicable)
If the use case matches event organizers / startup founders / gig-economy workers → load the template from references/use-cases.md and propose it as the starting point. Make clear they can fork/adapt.
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.
- 6d ago First seen · 164 lines · 21 tokens per session scan A 25e212efad2d
design-survey is a command published in the GitHub repository ooiyeefei/ccc (484 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 1,415 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.