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 skills/sdewell/code-quorum/q-brainstormnpx skills add sdewell/code-quorum --skill q-brainstormgit clone --depth 1 https://github.com/sdewell/code-quorumWhat 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 | $0.00086 | $0.03577 |
| Opus 5 | $0.00043 | $0.01788 |
| Sonnet 5 | $0.00017 | $0.00715 |
| Haiku 4.5 | $0.00009 | $0.00358 |
Grade A, and why
q-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 yesterday.
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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Q-Brainstorm — divergent ideas from each registered agent
Completion gate
For every council start, q_await is the blocking completion notification. After completing the host's independent work, call it in the same turn as the start. Do not end the turn, tell the user you will check later, or leave a live job_id pending. If the council is still running, remain in the blocking call until it returns a result or error.
Research-first: unless --no-research is passed, the run grounds itself in
prior art (arXiv + OpenAlex + Europe PMC published/preprints + Context7 +
GitHub + HuggingFace)
before the council generates, and the digest is seeded into the agents'
round-1 prompt as evidence. It is a research mode — treat the whole run as one.
Arguments
$ARGUMENTS is the brainstorm topic, optionally with flags:
--no-research— skip the prior-art grounding (research is the default).--extended— add a host-driven second round that diverges past round 1.--verbose— lift the terse output caps. Default is terse.--gemini-model <id>— run the gemini seat on a specific agy model.
Strip the flags from the topic text before passing topic to the tools. If the
topic (after removing flags) is empty, ask the user what they want to brainstorm.
Host routing
Claude Code uses the mcp__plugin_code-quorum_quorum__* tools and passes
host: "claude". Codex uses the mcp__quorum_codex__* tools and passes
host: "codex". The workflows are otherwise identical.
If either required MCP tool is absent from the current task's tool registry, stop and report that the plugin MCP server did not load. Do not substitute the synchronous CLI, direct Python imports, or another runtime path: only the registered start/await pair enforces the structural anti-bias gate.
Every MCP council start requires an explicit absolute cwd. Never omit it: the
MCP server's own working directory is its installation or runtime location, not
the project selected by the user.
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.
- yesterday First seen · 246 lines · 86 tokens per session scan A 25a8ae230c3d
q-brainstorm is a skill published in the GitHub repository sdewell/code-quorum (0 stars, last pushed 2d ago), licensed MIT. It adds 86 tokens to every session and 3,577 once invoked, about $0.0004 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
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
cross-squad-communication
Protocol for sending queries, delegating tasks, and sharing context between independent Squad instances across different repositories.
reviewer-protocol
Reviewer rejection workflow and strict lockout semantics.
oma-coordination
Guide for coordinating PM, Frontend, Backend, Mobile, and QA agents on complex projects via CLI. Use for manual step-by-step coordination and workflow guidance.
agent-conduct
Shared hard rules enforced across all squad agents.
agentic-workflow-designer
Conversational skill that interviews users to design new agentic workflows.