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/askwigconsulting/cohortWrote 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/askwigconsulting/cohort/brainstorm)<a href="https://agentmods.dev/commands/askwigconsulting/cohort/brainstorm"><img src="https://agentmods.dev/badge/commands/askwigconsulting/cohort/brainstorm/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/askwigconsulting/cohort/brainstorm"><img src="https://agentmods.dev/badge/commands/askwigconsulting/cohort/brainstorm.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00059 | $0.02919 |
| Opus 5.5 | $0.00024 | $0.01168 |
| Sonnet 5.5 | $0.00012 | $0.00584 |
| Haiku 4.5 | $0.00006 | $0.00292 |
Grade A, and why
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 1mo 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/brainstorm is the generative sibling of /audit. /audit finds what is wrong with
what exists; /brainstorm finds what could exist. It runs the same machinery — recurring,
on a rotation, cross-vendor, ledger-backed, coordinator-synthesized, and read-only /
advisory — but deliberately inverts it wherever creativity demands the opposite of
critique.
Run it from a coordinator tier (Fable preferred, Opus acceptable). Reviewers and generators
are advisory — they generate and evaluate; the coordinator synthesizes; the human
decides what to pursue. Producing anything real (a spike, a prototype, a research run) is
/scout's or /crew's job, never this command's.
The one discipline: diverge before you converge
The single failure that kills a brainstorm is letting judgment into the room too early. An agent asked to generate and evaluate in one breath produces three safe, obvious ideas and self-censors the non-obvious one — which was the entire point. So the phases are strictly separated and never share a prompt:
- Diverge — generate quantity, defer all judgment, chase the non-obvious.
- Converge — only now cluster, score, and red-team; kill the weak.
- Pursue — turn the survivors into the cheapest experiment that could validate or kill each one.
And like /audit, it rotates with a ledger, so it builds cumulatively instead of
re-generating the same five ideas every run. Two rules make that sound:
- Every open question gets a look. The project declares its open questions / opportunity areas in the ledger; nothing goes more than a few runs without a brainstorm aimed at it.
- A dead idea stays dead. An idea the convergence step killed is logged with the
reason, so a later run doesn't burn a generator re-proposing it — the generative analog
of
/audit's "don't re-litigate a struck finding." New evidence can revive it; a fresh restatement cannot.
1. Frame — read the ledger first
Read docs/brainstorm/ledger.md (create it on the first run). It records, per focus area:
ideas generated, which were pursued / parked / killed (and why), and the project's
declared opportunity areas and decision context — the goals, constraints,
differentiators-to-beat, and non-negotiables that keep ideation grounded rather than random.
Then read the project's own context (.cohort/project_context.md — its purpose, decisions,
and open questions; those open questions are the richest fuel there is).
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.
- 1mo ago First seen · 188 lines · 59 tokens per session scan A 860017cf58cb
brainstorm is a command published in the GitHub repository askwigconsulting/cohort (2 stars, last pushed 18d ago), licensed MIT. It adds 59 tokens to every session and 2,919 once invoked, about $0.0002 per session on Opus 5.5. 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 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.
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.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.