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/vrennat/developersdevelopers/brainstormgit clone --depth 1 https://github.com/vrennat/developersDevelopersWhat 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 | $0.00033 | $0.00458 |
| Opus 5 | $0.00016 | $0.00229 |
| Sonnet 5 | $0.00007 | $0.00092 |
| Haiku 4.5 | $0.00003 | $0.00046 |
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 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.
What it actually says
/brainstorm
Turn an idea into a written spec. Lean version: confirm only when there is genuine ambiguity. Default to your strongest recommendation; do not pause for "approve this section?" gates.
Procedure
- Read the user's idea. Skim project context (recent commits, existing docs in
docs/specs/anddocs/plans/, top-level CLAUDE.md). - Identify any genuinely ambiguous points: 2+ approaches with real tradeoffs, missing requirements, or scope decisions only the user can make. If none, skip to step 4.
- Ask all genuinely-ambiguous points in ONE batched message (numbered list). Wait for response. Do not ask one-at-a-time unless the next question depends on the prior answer.
- Draft the spec internally:
- Overview, goals, non-goals
- Architecture / approach (your recommended path; mention alternatives only if you genuinely think the user might want one)
- Open questions for implementation (resolved with defaults, not TBDs)
- Acceptance criteria
- Write the spec to
docs/specs/YYYY-MM-DD-<slug>-design.md. Today's date, lowercase-dashed slug. - Commit it:
docs: initial design spec for <slug>. - Tell the user where it is. Do NOT auto-trigger
/implor/plan.
Rules
- "Approve this section?" gates are forbidden. The whole spec is one artifact for review at the end, not five.
- Recommend, don't ask "what do you think?" — make the call, justify it in one sentence.
- "Open questions" must have a default decision next to them, not "TBD".
- If the spec covers >1 independent subsystem, decompose. Each subsystem gets its own spec.
Anti-patterns
- Asking the user to pick between two equivalent options. If equivalent, pick one.
- Writing a 500-line spec for a 50-line feature.
- Asking permission to start writing.
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 · 36 lines · 0 tokens per session scan A 9747163438c4
brainstorm is a command published in the GitHub repository vrennat/developersDevelopers (2 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 458 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 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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
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.