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 skills add yike-gunshi/forge-skills --skill forge-brainstormgit clone --depth 1 https://github.com/yike-gunshi/forge-skillsWrote 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/yike-gunshi/forge-skills/forge-brainstorm)<a href="https://agentmods.dev/skills/yike-gunshi/forge-skills/forge-brainstorm"><img src="https://agentmods.dev/badge/skills/yike-gunshi/forge-skills/forge-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/yike-gunshi/forge-skills/forge-brainstorm"><img src="https://agentmods.dev/badge/skills/yike-gunshi/forge-skills/forge-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 | $0.00115 | $0.04227 |
| Opus 5 | $0.00057 | $0.02114 |
| Sonnet 5 | $0.00023 | $0.00845 |
| Haiku 4.5 | $0.00012 | $0.00423 |
Grade A, and why
forge-brainstorm scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.
文档落地路径:遵循 forge-doc-policy 规范。完整白名单 + frontmatter schema 见
~/.claude/skills/forge-doc-policy/doc-paths.md。 当前文档加载顺序:先读项目CLAUDE.md、docs/README.md、docs/INDEX.md。 需要写入当前事实时进入根级当前真相源;brainstorm 原始讨论默认进入 archive/raw。 详细规则见~/.claude/skills/_shared/current-doc-loading.md。
/forge-brainstorm:通用头脑风暴
任何时候、任何话题。讨论完用户自己决定下一步。
全程中文。
铁律
- 一次一个问题 — 不要连续抛出多个问题。优先选择题,减少用户认知负担。
- 反谄媚 — 禁止说"有趣的想法"、"很好的思路"、"有很多种方式"。直接给判断。
- 证据先于断言 — 不说"这应该可行",要说"基于 X 证据,Y 方案可行因为 Z"。
- 不要替用户做决定 — 给方案、给推荐、给理由,但最终选择权在用户。
- 急躁逃生口 — 用户任何时候说"别问了"、"直接给方案"、"跳过",立即跳到 Phase 4。
前置脚本(每次先运行)
_ROOT=$(git rev-parse --show-toplevel 2>/dev/null || pwd)
echo "项目根目录: $_ROOT"
# 检测项目类型
[ -f "$_ROOT/package.json" ] && echo "检测到: Node.js 项目"
[ -f "$_ROOT/requirements.txt" ] && echo "检测到: Python 项目"
[ -f "$_ROOT/go.mod" ] && echo "检测到: Go 项目"
[ -f "$_ROOT/Cargo.toml" ] && echo "检测到: Rust 项目"
# 检查已有文档
[ -f "$_ROOT/docs/README.md" ] && echo "发现 docs/README.md"
[ -f "$_ROOT/docs/INDEX.md" ] && echo "发现 docs/INDEX.md"
[ -f "$_ROOT/docs/modules/doc-system.md" ] && echo "发现项目文档系统说明"
[ -f "$_ROOT/docs/PRD.md" ] && echo "发现 PRD" && head -20 "$_ROOT/docs/PRD.md"
[ -f "$_ROOT/docs/DESIGN.md" ] && echo "发现 DESIGN.md"
[ -f "$_ROOT/docs/ENGINEERING.md" ] && echo "发现 ENGINEERING.md"
# 检查已有 brainstorm 文档
ls -d "$_ROOT/docs/archive/raw/discussions/"*/ 2>/dev/null && echo "发现 archive/raw discussions(当前推荐归档)"
ls -d "$_ROOT/docs/讨论/"*/ 2>/dev/null && echo "发现 legacy docs/讨论/ 子目录"
ls "$_ROOT/docs/brainstorm-"*.md 2>/dev/null && echo "发现历史思考文档(旧约定)"
ls "$_ROOT/brainstorm-"*.md 2>/dev/null && echo "发现历史思考文档(根目录)"
Phase 0:上下文感知 + 模式检测
步骤
- 运行前置脚本 — 了解项目环境和已有文档
- 如果在项目目录中 — 快速扫描项目结构(Glob + 读取关键文件),理解当前状态
- 听用户说 — 用户描述他在想什么。不要打断,不要急着分类。
- 自动检测模式 — 根据用户描述的内容,判断最合适的模式
- AskUserQuestion 确认模式:
我判断这次讨论适合【{模式名}】模式。
A) {模式名} — {一句话描述}
B) 产品模式 — 工程项目/功能设计/系统架构
C) 内容模式 — 写文章/演讲/内容策划
D) 构建模式 — 小demo/POC/学习项目/黑客松
E) 探索模式 — 方向不明确,先聊聊
选哪个?
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 316 lines · 115 tokens per session scan A 5939dd5b4f5a
forge-brainstorm is a skill published in the GitHub repository yike-gunshi/forge-skills (13 stars, last pushed 1mo ago), licensed MIT. It adds 115 tokens to every session and 4,227 once invoked, about $0.0006 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 skills, from other repositories
vastai
Vast.ai CLI to manage GPU instances, volumes, serverless endpoints, and billing.
vastai-sdk
Vast.ai Python SDK — high-level API for GPU instances, volumes, serverless endpoints, and billing.
forge-evolution
Autonomous persona evolution pipeline for failure-driven capability growth.
docs-context
Super Base Context — project doc loader & synchronizer. Triggers even without explicit "load docs"/"sync docs." READ MODE — load architecture/modules/coding/decision docs when work references project state: code work (write/modify/remove); design (features/APIs/schemas/architecture); review (modules, past solutions)…
houtu-dependencies
Skill "houtu-dependencies" from lujiafa/houtu-project-skills, covering houtu framework — ai agent coding guide, core principles, code generation workflow (must be executed in order), step 1 — detect version & dependencies and step 2 — identify scenario & select module.
senzing-entity-resolution
Guides AI agents through Senzing entity resolution workflows using the Senzing MCP server. Covers data mapping to Senzing format, SDK code generation (Python, Java, C#, Rust, TypeScript/Node.js), documentation search, error troubleshooting, sample data access, reporting and visualization, SDK setup guides, and…