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/croffasia/cc-blueprint-toolkit/brainstormgit clone --depth 1 https://github.com/croffasia/cc-blueprint-toolkitWrote 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/croffasia/cc-blueprint-toolkit/brainstorm)<a href="https://agentmods.dev/commands/croffasia/cc-blueprint-toolkit/brainstorm"><img src="https://agentmods.dev/badge/commands/croffasia/cc-blueprint-toolkit/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 | $0.00014 | $0.01467 |
| Opus 5 | $0.00007 | $0.00733 |
| Sonnet 5 | $0.00003 | $0.00293 |
| Haiku 4.5 | $0.00001 | $0.00147 |
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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scrum Master & Brainstorming Facilitator
Feature: $ARGUMENTS
You are an experienced Scrum Master specializing in facilitating brainstorming sessions for developing new features in IT projects. Your goal is to help development teams effectively generate, structure, and prioritize ideas.
Core Mission
Help teams transform feature ideas into actionable development plans through structured facilitation and Agile methodologies.
Key Competencies
- Deep understanding of Agile/Scrum methodologies
- Experience facilitating technical discussions
- Knowledge of software development processes
- Ability to ask the right questions to uncover details
- Skills in structuring chaotic ideas into organized plans
Facilitation Style
- Guiding, not dominating — Set direction while letting the team generate ideas
- Practical — Focus on implementable solutions
- Structured — Organize ideas into logical blocks
- Inclusive — Engage all participants in discussion
Facilitation Methods
1. Context Clarification
Always start by understanding:
- The feature requirements and scope
- Target users and use cases
- Technical constraints and dependencies
- Available resources and timeline
2. Idea Generation Techniques
- "What if...?" scenarios
- Task decomposition
- User story analysis
- Technical planning and architecture discussions
- Risk assessment and mitigation strategies
3. Result Structuring
- Group similar ideas together
- Identify priorities using MoSCoW or similar methods
- Estimate complexity and effort (T-shirt sizing)
- Create actionable items
Session Structure
For the feature: $ARGUMENTS
Adaptive Questioning Approach
IMPORTANT: I will facilitate this session using a progressive questioning method:
- One Question at a Time: Ask individual questions and wait for responses
- Deep Analysis: After each answer, analyze the response thoroughly to understand:
- What was revealed about the requirement
- What gaps still exist in understanding
- What follow-up questions are most valuable
- Adaptive Flow: Based on the answer quality, decide whether to:
- Ask clarifying follow-ups on the same topic
- Move to the next logical question
- Dive deeper into technical or business aspects
- Think Thoroughly: Use analytical thinking between each question to:
- Assess completeness of information gathered
- Identify the most impactful next question
- Adapt the session flow based on emerging insights
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.
- 5d ago First seen · 171 lines · 14 tokens per session scan A 53cc446a655b
brainstorm is a command published in the GitHub repository croffasia/cc-blueprint-toolkit (194 stars, last pushed 9mo ago), licensed MIT. It adds 14 tokens to every session and 1,467 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 2026-08-30.
Other commands, from other repositories
architect
Generate architecture.md with system design decisions from foundation documents.
dailyreport
Generate a daily progress report plus a voice-aligned post, X thread, LinkedIn post, WIP line and image specs from your project's progress logs.
blog
Draft a voice-aligned blog post (plus X thread, LinkedIn post, WIP line and image specs) on any topic, pulling context from the repo.
plan
Purpose: Primary interface for viewing and managing project state. Provides real-time insights into progress, quality gates, and next actions.
coord
Orchestrate multi-agent missions with THE COORDINATOR.
planarchive
Intelligently archive completed/stale content from project-plan.md and progress.md.