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/abderrahimghazali/hivemind/brainstormgit clone --depth 1 https://github.com/abderrahimghazali/hivemindWrote 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/abderrahimghazali/hivemind/brainstorm)<a href="https://agentmods.dev/commands/abderrahimghazali/hivemind/brainstorm"><img src="https://agentmods.dev/badge/commands/abderrahimghazali/hivemind/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 | $0.00010 | $0.00372 |
| Opus 5 | $0.00005 | $0.00186 |
| Sonnet 5 | $0.00002 | $0.00074 |
| Haiku 4.5 | $0.00001 | $0.00037 |
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 4d 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.
What it actually says
You are brainstorming a topic with Codex. Goal: explore the topic together over up to 3 rounds, then converge on a recommendation.
Setup: call mcp__hivemind__peers once. If Codex is offline or reports unsupported_session_picker, surface the error and stop.
Round structure (repeat up to 3 times, fewer if you reach consensus or hit a hard disagreement):
- State your current view in 2-4 sentences. Tag a key conclusion with
[IMPORTANT]if you have one — this is a hint to Codex, not a routing rule. - Send your view to Codex via
mcp__hivemind__ask_codexwithwait_ms: 90000. The tool returns Codex's reply. - If you got a reply: identify points of agreement and points of disagreement explicitly. Use phrases like "I agree on:", "I disagree on:", "Current consensus:".
- Decide whether to continue:
- Stop early if you have converged (both sides agree on a path).
- Stop early if the disagreement is substantive and unresolved — that itself is the answer.
- Otherwise, run another round.
Final summary (always):
- Convergent ideas: what you both agree on.
- Divergent ideas: what you disagree on, with the strongest argument from each side.
- Recommended next step: one concrete action.
Topic: $ARGUMENTS
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.
- 4d ago First seen · 28 lines · 10 tokens per session scan A 68a49d82598d
brainstorm is a command published in the GitHub repository abderrahimghazali/hivemind (2 stars, last pushed 4mo ago), licensed MIT. It adds 10 tokens to every session and 372 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 2026-08-31.
Other commands, from other repositories
upgrade-webkit
Upgrade Bun's WebKit fork to the latest upstream version of WebKit.
dedupe
Find duplicate GitHub issues.
ashlr-dashboard
Rich token-savings dashboard — per-tool bar charts, 7d/30d sparklines, projected annual savings, and cost in dollars.
scriptwriter-draw
Draw a random chaos card from the 13-card deck — a plot-twist prompt the user can use as a scene seed, a basistext for an RRR cascade, or a riff for a room contribution.
specsync-create-spec
Create a new spec-sync module spec.
docs
Documentation hub - explain code, generate docs, feature overviews.