brainstorm-loop

A workflow for generating many different approaches to a feature, testing the leading ideas against possible failures, and choosing one.

In plain words
What is it for?
Use it when deciding how to build something, starting with brainstorming, then a pre-mortem—imagining why each idea failed—and finally a recorded choice.
Why use it?
It helps avoid settling on the first obvious solution and exposes risks 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/sjarmak/coding-agent-workflows/brainstorm-loop
Clone the repo
git clone --depth 1 https://github.com/sjarmak/coding-agent-workflows
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 329 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 $0.00021 $0.00329
Opus 5 $0.00010 $0.00164
Sonnet 5 $0.00004 $0.00066
Haiku 4.5 $0.00002 $0.00033

Measured yesterday against content hash 53ca223ac25c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

brainstorm-loop 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.

targets/claude/commands/brainstorm-loop.md · 42 lines

What it actually says

Workflow: Brainstorm Loop

For feature design and "how should we approach X" questions. Forces divergent volume under a uniqueness constraint, then filters by failure analysis.

Inputs

Input Source Description
problem caller The problem statement. Use the task title if dispatched.
context caller Constraints and prior art that define exclusion zones.

Steps

1. brainstorm

Run brainstorm: produce many candidate approaches under one hard constraint. No idea may take the same shape as any prior art or any earlier idea in this session. Volume plus shape-uniqueness is what gets past the obvious answer.

Exit: a set of shape-distinct candidates.

2. premortem (needs: brainstorm)

Run premortem on the top candidates: for each, assume it failed and list why. Drop candidates whose failure modes are fatal or unmitigable.

Exit: a shortlist of candidates that survive failure analysis.

3. converge (needs: premortem)

Run converge on the shortlist: pick one direction, state the trade-offs it accepts, and record the runners-up so the decision is auditable later. Where subagents are available, run it as a multi-agent debate; otherwise weigh the shortlist directly in one pass.

Exit: one chosen direction + rejected alternatives with reasons.

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. yesterday First seen · 42 lines · 21 tokens per session scan A 53ca223ac25c

Subscribe to this mod's changes

brainstorm-loop is a command published in the GitHub repository sjarmak/coding-agent-workflows (2 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 329 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.