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 xiqin/loom --skill loom-brainstorminggit clone --depth 1 https://github.com/xiqin/loomWrote 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/xiqin/loom/loom-brainstorming)<a href="https://agentmods.dev/skills/xiqin/loom/loom-brainstorming"><img src="https://agentmods.dev/badge/skills/xiqin/loom/loom-brainstorming/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/xiqin/loom/loom-brainstorming"><img src="https://agentmods.dev/badge/skills/xiqin/loom/loom-brainstorming.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 | $0.00047 | $0.01688 |
| Opus 5 | $0.00023 | $0.00844 |
| Sonnet 5 | $0.00009 | $0.00338 |
| Haiku 4.5 | $0.00005 | $0.00169 |
Grade A, and why
loom-brainstorming 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 9d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
需求头脑风暴
触发条件
- 用户提出新需求、功能描述或 PRD。
- 用户询问设计方案、实现路径或技术 trade-off。
- 需求存在关键歧义、涉及多角色/权限/业务规则,或验收标准不清。
非触发条件
- 单文件 typo、文案、配置微调或用户已给出明确验收标准的小改动。
- 根因已明确且范围很小的 bug 修复;这类任务应交给
loom-pipeline-selector命中 quickfix/bugfix 流程。
执行流程
产物根目录
本阶段应创建或使用 specs/<date+feature>/ 作为 specDir。所有阶段产物都必须写入该目录内;禁止在项目根目录写 spec.md、progress.md 或 handoffs/。
Step 1:理解需求
- 若存在
.loom/rules/product.md,先读取,作为产品定位、目标用户和原型约束的视角依据(PM / pm-prototype 流水线)。 - 若存在
.loom/rules/constitution.md,读取其中架构、目录和编码约束。 - 修改类需求先分析现有实现和影响范围。
- 明确边界:做什么、不做什么。
Step 2:可视化伴侣(可选)
如果预计涉及模型、布局、架构图等可视化内容,单独询问用户是否使用浏览器展示。详细流程见 references/visual-companion.md。
Step 3:探索 2-3 种方案
每个方案包含:方案名称、架构思路、数据流、trade-off、实现步骤。以推荐方案开头并解释原因;如果范围跨多个独立子系统,先建议拆分。
Step 4:澄清与 shared understanding
先区分问题来源:能通过读取代码、文档、spec 或现有约定回答的问题,必须先自行探索,不要问用户。
对简单需求,把待决议项集中展示给用户,优先给多选项:
## 待决议项
| # | 问题 | 选项 |
| --- | -------------- | --------------------------------- |
| 1 | 数据存储方式? | A: 关系型数据库 / B: 文档型数据库 |
对复杂需求进入一问一答澄清:
- 沿最阻塞的设计分支提一个问题。
- 每次只问一个问题。
- 给出推荐答案和理由。
- 等待用户反馈后再问下一个问题。
- 用户确认 shared understanding 前,不写最终 spec,不进入实现。
Step 5:输出 spec.md 与 requirements.json
用户确认方案后,写入 specs/<date+feature>/spec.md 和 specs/<date+feature>/requirements.json。文件夹命名格式:<YYYY-MM-DD>+<功能名>,如 2026-04-26+user-management。
使用 assets/spec-template.md 作为结构模板,并按项目类型删去不适用章节。
requirements.json 必须与 spec.md 的所有 REQ-xxx 一一对应。每个 requirement 必须包含:
id:如REQ-001。status:初始为failing。types:需求类型,如functional、input、authorization、write、state、security、performance、observable、recovery。required_categories:该需求必须覆盖的行为维度,如happy-path、invalid-input、authorization、atomicity、state-transition、observability。acceptance:需求级验收标准。behaviors:可独立验证的行为义务,ID 使用REQ-xxx-Bnn,每条必须有category、description、status、acceptance。
行为维度必须从以下白名单选择:happy-path、boundary、invalid-input、authorization、state-transition、idempotency、concurrency、atomicity、external-failure、compatibility、security、performance、observability、recovery、forbidden-behavior。
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.
- 9d ago First seen · 128 lines · 47 tokens per session scan A 421224f21134
loom-brainstorming is a skill published in the GitHub repository xiqin/loom (5 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 1,688 once invoked, about $0.0002 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…