Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add sentasity/cadence/plugin install cadenceWrote 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/sentasity/cadence/c-brainstorm)<a href="https://agentmods.dev/skills/sentasity/cadence/c-brainstorm"><img src="https://agentmods.dev/badge/skills/sentasity/cadence/c-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 | $0.00115 | $0.02689 |
| Opus 5 | $0.00057 | $0.01345 |
| Sonnet 5 | $0.00023 | $0.00538 |
| Haiku 4.5 | $0.00012 | $0.00269 |
Grade A, and why
c-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 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/c-brainstorm
You drive an interactive brainstorming Q&A. The session runs in one of two modes:
- Thought-partner mode — exploratory; helps the user think through an idea or small question; ends when the user is satisfied; writes nothing unless they ask.
- Design-brainstorm mode — converges on a concrete approach; ends by writing a single
00-overview.mdstub.
You never write child docs, plans, or code. You never auto-promote into /c-design.
Hard gate: every AskUserQuestion (no exceptions)
Before sending ANY question — including casual "what next?" / "which thread first?" menus in the middle of a thought-partner chat — it MUST pass all three checks. This is not optional and not relaxed by conversational flow. If a question can't pass, it is not ready to send.
- Plain-English lead, at the top. The
questionfield opens with a sentence a newcomer could follow — what we're deciding and why it matters right now. A bare"What next?"or a terse label fails this gate. The user must understand what's going on from the question text alone. - Exactly one
(Recommended)option, listed first. Append(Recommended)to that option's label and put it in position 1. Triage/exploration menus are NOT exempt — "it's your call" is a non-answer; pick the one you'd tackle first and say why. If which one you'd recommend depends on state, put whichever you're recommending this time first. - Each option's
descriptionstates the trade-off in one sentence — what you get, what you give up.
Full spec + worked bad→good example: skills/_shared/ask-user-question.md. Read it if you haven't this session.
Invocation forms
/c-brainstorm <idea text>— start fresh with the user's idea. Detect mode from phrasing (see "Mode detection" below)./c-brainstorm(no args) — ask: "What are we tackling?" before entering Q&A./c-brainstorm --explore <topic>— force thought-partner mode./c-brainstorm --design <topic>— force design-brainstorm mode.
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 · 133 lines · 115 tokens per session scan A b4643a3346d1
c-brainstorm is a skill published in the GitHub repository sentasity/cadence (1 stars, last pushed 12d ago), licensed MIT. It adds 115 tokens to every session and 2,689 once invoked, about $0.0006 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
self-improve
Self-improve this skills repo — surface and (safely) apply quality improvements across four parallel read-only lenses (Clarity, Leanness, Coverage, Ergonomics). Sibling of /self-audit — audit fixes rule violations, improve raises quality where no rule is broken. Local meta-skill, independent of the /task: pipeline.
self-audit
Self-audit this skills repo against CLAUDE.md invariants, the artifact contract, and README/CLAUDE.md/docs sync via three parallel read-only subagents. Local meta-skill — independent of the /task: pipeline.
grill
Interrogate a plan or decision one question at a time before capture, keeping a decision-plus-rationale ledger, then route to the right capture skill.
batch
Dispatch a night's batch of Todo tickets — one worktree and one pull request each — and leave a morning summary. Run explicitly; never inferred.
cleanup
Clean up after a merged pull request — return to the base branch, remove the worktree, delete the branch, sweep other stale branches and worktrees, and report tracker state. Use after a merge or whenever asked what is left over.
prep
Spec a ticket before it is dispatched. Brainstorms it, decides everything it can recommend an answer for, asks a present human about the little that survives, and leaves the spec, the decisions and anything still open as one ticket comment. No worktree, no branch, no pull request, and the ticket stays where it was.