Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add cukas/claudes-ai-buddies/plugin install claudes-ai-buddiesWrote 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/skills/cukas/claudes-ai-buddies/brainstorm)<a href="https://agentmods.dev/skills/cukas/claudes-ai-buddies/brainstorm"><img src="https://agentmods.dev/badge/skills/cukas/claudes-ai-buddies/brainstorm/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/cukas/claudes-ai-buddies/brainstorm"><img src="https://agentmods.dev/badge/skills/cukas/claudes-ai-buddies/brainstorm.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00023 | $0.01291 |
| Opus 5 | $0.00012 | $0.00646 |
| Sonnet 5 | $0.00005 | $0.00258 |
| Haiku 4.5 | $0.00002 | $0.00129 |
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 10d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/brainstorm — Multi-AI Confidence Bid
Each available AI engine assesses a task (implementation, bug fix, refactor, etc.), gives a realistic confidence rating, and proposes their approach. The user picks who takes it.
How to invoke
The user says /brainstorm "task description".
Step-by-step workflow
- Parse the task. Extract what the user wants done from their message.
- Build the assessment prompt. Wrap the user's task with this framing for Codex and Gemini:
Assess this task honestly. You are bidding alongside other AI engines — the user will pick who handles it. Be realistic, not optimistic.
Respond in EXACTLY this format (no other text):
CONFIDENCE: [0-100]%
APPROACH: [2-3 sentences max — what you'd do, step by step]
RISKS: [1-2 key risks or unknowns that could trip you up]
NEEDS: [what you'd need from the user — files, context, access, clarification]
Task: USER_TASK_HERE
-
Build conversation context (if relevant). Use your judgment — if the conversation has context the buddies need (constraints, failed approaches, user preferences), summarize it in
$CONVERSATION_CONTEXT. If the task is self-contained, leave it empty. Keep under ~500 tokens. -
Detect available buddies and run them in parallel. Use the dynamic registry:
source "${CLAUDE_PLUGIN_ROOT}/hooks/lib.sh"
AVAILABLE=$(ai_buddies_available_buddies) # CSV: "claude,codex,gemini,aider,..."
For each available buddy (excluding claude — you ARE claude), dispatch in parallel:
# For each buddy ID in the available list:
ai_buddies_dispatch_buddy "BUDDY_ID" "$(pwd)" "ASSESSMENT_PROMPT" 360 "/tmp" "${CLAUDE_PLUGIN_ROOT}" "$CONVERSATION_CONTEXT"
Or use the specific adapter scripts for builtin buddies (codex-run.sh, gemini-run.sh).
IMPORTANT: When calling via the Bash tool, set timeout to 420000 (7 minutes). Codex and OpenCode regularly take 3-6 minutes — the default Bash timeout (120s) will kill them.
Cap at top 4 buddies to keep the table readable.
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.
- 10d ago First seen · 118 lines · 23 tokens per session scan A 8f04b03b9aea
brainstorm is a skill published in the GitHub repository cukas/claudes-ai-buddies (9 stars, last pushed 4mo ago), licensed MIT. It adds 23 tokens to every session and 1,291 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.
Other skills, from other repositories
optimize-claude-fable-5-prompts
A prompt-editing method for Claude Fable 5, an AI model. It turns rough or existing instructions into clearer prompts while keeping the original goal and important limits.
optimize-claude-opus-5-prompts
Clarify, audit, and rewrite rough or existing prompts for Claude Opus 5 using Anthropic's official prompting guidance. Use when a user asks to optimize, improve, migrate, debug, or design a prompt, system prompt, or agent harness for Claude Opus 5 (claude-opus-5), including requests phrased as Opus 5 prompt…
optimize-gpt-5-6-prompts
A guide for improving prompts written for OpenAI’s GPT-5.6 models, including GPT-5.6 Sol.
optimize-gpt-6-astra-prompts
Clarify, audit, migrate, and rewrite prompts for GPT-6 Astra using OpenAI's official latest-model prompting guidance. Use when a user asks to optimize, improve, rewrite, debug, migrate, or design a GPT-6 Astra prompt, including requests phrased as GPT-6, Astra, or gpt-6-astra prompt optimization, or when an…
optimize-deepseek-v4-prompts
Clarify, audit, and rewrite rough or existing prompts specifically for DeepSeek-V4 Pro and Flash using the DeepSeek-AI V4 technical report as the model-specific evidence base. Use when a user asks to optimize, improve, rewrite, debug, migrate, or design a DeepSeek-V4 prompt, including requests phrased as DeepSeek…
optimize-gemini-prompts
A prompt-editing skill for clarifying and rewriting prompts intended for Google’s Gemini models.