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 ChianW/C31 --skill c31-brainstormgit clone --depth 1 https://github.com/ChianW/C31Wrote 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/chianw/c31/c31-brainstorm)<a href="https://agentmods.dev/skills/chianw/c31/c31-brainstorm"><img src="https://agentmods.dev/badge/skills/chianw/c31/c31-brainstorm.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 | $0.00038 | $0.04018 |
| Opus 5 | $0.00019 | $0.02009 |
| Sonnet 5 | $0.00008 | $0.00804 |
| Haiku 4.5 | $0.00004 | $0.00402 |
Grade A, and why
C31-brainstorm 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 8d 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 — 336 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multilingual Triggers
| Language | Trigger phrases |
|---|---|
| EN | brainstorm, ideate, think through, 需求, discuss, 讨论, discuss-phase |
| ZH | 头脑风暴, 讨论需求, 讨论一下 |
| JA | ブレインストーミング, 考えてみよう, 議論しよう |
Output language: Respond automatically in the user's conversation language.
C31 Brainstorm — Discuss Phase
Brainstorming answers WHAT to build. It precedes planning, which answers HOW to build it.
The durable output is a requirements document with numbered, traceable decisions (D-01, D-02...) that MUST carry forward into planning. No decision made here should be silently re-invented later.
Guardrails: Anti-Rationalization Table
When requirements are fuzzy, agents commonly rationalize skipping structured discovery. Call yourself out.
| Excuse | Why It's Wrong | Correct Approach |
|---|---|---|
| "The user will tell me" | Users assume you already understand; they won't proactively fill in gaps | Actively extract, one question at a time |
| "Assume first, adjust later" | Assumptions will contaminate all downstream reasoning | Mark as A-XX, wait for confirmation |
| "Open-ended questions are efficient" | Users faced with a blank will skip or give vague answers | Offer options to narrow the answer space |
| "It's already clear enough" | Your "clear" ≠ the user's "clear" | Validate with concrete scenarios |
| "Asking more will annoy the user" | Rework after delivery is far more annoying | Every question has ROI |
Rule of thumb: If you can't write down 3 specific acceptance criteria right now, you don't understand the requirement well enough to plan.
Interview-me Mode
A structured variant of Phase 1.3 for when the user's request is genuinely ambiguous — not merely underspecified, but the problem space itself is unclear.
When to Activate
- You can't articulate the user's goal in one sentence
- You can't list 3 concrete acceptance criteria
- Your internal confidence score is < 70%
- The user said "I want to build a..." / "Can you help me..." with no follow-up detail
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.
- 8d ago First seen · 336 lines · 38 tokens per session scan A 7111513dc86e
C31-brainstorm is a skill published in the GitHub repository ChianW/C31 (1 stars, last pushed 13d ago), licensed MIT. It adds 38 tokens to every session and 4,018 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
compare-harnesses
Diff two scaffolded harnesses (ADR-031). Reports manifest meta drift + host list + per-file fingerprint changes (added/removed/changed). Exits 0 IDENTICAL, 1 DRIFT, 2 missing manifest. Use --bundle for the ADR-031 schema-1 JSON envelope.
oia-manifest
Emit .harness/oia-manifest.json declaring layer alignment with the OIA v0.1 9-layer reference architecture. Self-describes the harness's MCP wiring, witness signing, audit log, identity posture (always 'none' at v0.1). --check verifies an existing manifest, --dry-run prints without writing, --json emits to stdout.
create-harness
Scaffold your own focused AI agent harness — pick host (Claude Code, Codex, pi.dev, Hermes), template, agents, skills, and ship a npm-publishable harness with its own npx CLI. Use when a user asks to "create my own agent harness", "scaffold a harness", "make a custom Claude Code plugin like ruflo", or "build a…
diag-harness
Kernel-version skew check (ADR-027). Reports manifest surface + manifest kernel + installed kernel + verdict (match/patch-diff/minor-diff/major-diff). Exits 1 on minor/major skew with a copy-pasteable npm install @metaharness/[email protected] next step. Exits 2 if no .harness/manifest.json at path.
example-harness
Scaffold a ready-made AI agent harness in one command from the 19 published @metaharness/ example packages — 9 host integrations (Claude Code, Codex, Hermes, pi.dev, OpenClaw, RVM, Copilot, OpenCode, GitHub Actions) + 10 vertical pods (devops, research, trading, support, legal, coding, education, sales, gaming…
repo-genome
7-section readiness scorecard for a LOCAL repo. Reports repo type + agent topology + MCP risk + test confidence + release readiness + recommended harness plan + scorecard. Exit 0 ready, 1 needs-work, 2 blocked. --json for the 6-field scorecard, --bundle for the ADR-031 schema-1 envelope.