brainstorm

A planning command that surveys the current capabilities of an add-on and ranks possible improvements. It then asks another agent to write a build plan for the highest-value gap; it does not write code.

In plain words
What is it for?
Use it to find gaps, rank ideas by effort and value, and get a phased plan with files, tests, risks, and rollback notes.
Why use it?
It turns missing capabilities into concrete, reviewable proposals before implementation begins.

Command

Install

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.

agentmods
npx agentmods add commands/rasputinkaiser/self-improvement-plugin/brainstorm
Clone the repo
git clone --depth 1 https://github.com/RasputinKaiser/Self-Improvement-Plugin
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 442 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00039 $0.00442
Opus 5 $0.00019 $0.00221
Sonnet 5 $0.00008 $0.00088
Haiku 4.5 $0.00004 $0.00044

Measured 2d ago against content hash 2f05abdf5fd6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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.

commands/brainstorm.md · 29 lines

What it actually says

The JSON response also includes bounded idea_cards. Each card has a stable ID, source signal, leverage/effort, and a plan card using the Scout → Judge → Worker → verify sequence. Cards are suggestions only: brainstorm does not create tasks, write code, or claim that a suggested change has been verified.

Run python3 ${CLAUDE_PLUGIN_ROOT}/scripts/brainstorm.py --json to survey current capabilities and identify gaps. The response keeps the legacy gaps array and adds 3-5 ranked idea_cards, each with a stable ID, source signal, plan, effort estimate, and leverage score.

Read the result. Then dispatch the escalate agent to draft a full build plan for the highest-leverage gap (the top entry). Give the escalate agent:

  • The gap name and description
  • The current capability map (from references/capability_map.md in this plugin)
  • Instruction to produce: a phased plan with concrete file paths, new types/modules, UX patterns to borrow from Codex App / Claude Code, test strategy, and risk/rollback notes
  • Constraint: do NOT write any code — produce the plan only. The user will review and decide whether to implement.

Present the user with:

  1. Ranked gap list (3-5 items with effort + leverage scores)
  2. The escalated plan for the top gap (full architecture, phased build order)

Append a one-line summary to ${SIPS_HOME:-$HOME/.codex/sips}/improvements.md under ## /brainstorm sweep — <ts> noting what the top gap was and whether the escalate agent produced a plan.

Do not edit ${CLAUDE_PLUGIN_ROOT}/scripts/* or the SIPS plugin source beyond the journal append. If the escalate agent suggests code changes, surface them as proposals only - the user explicitly reviews before any implementation.

Changes

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.

  1. 2d ago First seen · 29 lines · 39 tokens per session scan A 2f05abdf5fd6

Subscribe to this mod's changes

brainstorm is a command published in the GitHub repository RasputinKaiser/Self-Improvement-Plugin (6 stars, last pushed 5d ago), licensed MIT. It adds 39 tokens to every session and 442 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.