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 alvis-HaoH/gkd/plugin install gkdWrote 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/alvis-haoh/gkd/brainstorm)<a href="https://agentmods.dev/commands/alvis-haoh/gkd/brainstorm"><img src="https://agentmods.dev/badge/commands/alvis-haoh/gkd/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/commands/alvis-haoh/gkd/brainstorm"><img src="https://agentmods.dev/badge/commands/alvis-haoh/gkd/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 | $0.00051 | $0.00752 |
| Opus 5.5 | $0.00020 | $0.00301 |
| Sonnet 5.5 | $0.00010 | $0.00150 |
| Haiku 4.5 | $0.00005 | $0.00075 |
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 1mo 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.
What it actually says
把多模型并行的独立意见交回综合。这是发散式形态——每个模型在干净独立的上下文里答题,彼此不可见,故意避开 sycophancy / 回声室效应。
原始参数:
$ARGUMENTS
怎么做
-
拣 flags:
--models a,b,c、--with-context、--effort <值>、--json、--quiet。--effort调思考强度(档位 none/low/medium/high/xhigh/max),两种粒度:统一档--effort xhigh(所有模型同档);按模型--effort glm:max,gpt:high(未列出的用各自默认)。用户说"让 X 深想""都用 max 想"之类就补上。 -
--with-context默认不带:brainstorm 的卖点是独立性,带主对话历史会污染独立性 + N 倍成本。只有用户显式要求、或问题强回指主对话(评估"上面的"那个方案)时才考虑。不确定时用AskUserQuestion问一次(带历史 / 干净独立答题)。 -
跑(问题文本第一个非 flag token 起,保留换行,永远
run_in_background: true——N 模型并行,最慢那个常超 2 分钟):
node "${CLAUDE_PLUGIN_ROOT}/scripts/gkd-brainstorm.mjs" <拣出的 flags> "$(cat <<'__GKD_QUESTION_EOF__'
<问题原文,保留换行>
__GKD_QUESTION_EOF__
)"
单引号 heredoc 终止符 + 外层 "$(...)" 包成单个 argv 参数。报 task_id 给用户,收到 <task-notification> 后 Read .output 拿 stdout(===== <model> ===== 分块)。
综合给用户
别把 N 份完整答案原样贴出来(那样白用 brainstorm)。你的价值是提炼:用自己的话讲清每个模型的核心主张,明确指出共识(哪点稳)、分歧(谁说什么、差在哪)、独到见解(只有某个模型提到但有道理的点——这是多模型的核心价值),最后给一份明确判断,不骑墙。始终标明观点来自哪个模型,别假装是自己想的,也别"修正"某个模型的视角差异(那些差异正是想要的)。
末尾一行汇报:参与: <实际参与的模型>;失败: (若有则列出哪个为什么)。===== <model> (FAILED) ===== 块表示该模型失败,综合时跳过但务必告诉用户哪些没参与,以免他以为全员都说没问题。
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.
- 1mo ago First seen · 37 lines · 51 tokens per session scan A 1a4a244c2048
brainstorm is a command published in the GitHub repository alvis-HaoH/gkd (11 stars, last pushed 3mo ago), licensed MIT. It adds 51 tokens to every session and 752 once invoked, about $0.0002 per session on Opus 5.5. 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
debug
Systematic debugging with hypotheses and evidence gathering.
review
Structured code review with severity categorization (distinct from Claude Code's PR review).
sparring
Adversarial brainstorming - challenge ideas, find weaknesses.
think
Apply structured thinking frameworks to a problem.
resume
Continue a cli-dispatch worker session with a follow-up prompt (auto-detects backend).
haiku
Switch to Haiku model (fast, cheap).