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-writing-plansgit 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-writing-plans)<a href="https://agentmods.dev/skills/xiqin/loom/loom-writing-plans"><img src="https://agentmods.dev/badge/skills/xiqin/loom/loom-writing-plans/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-writing-plans"><img src="https://agentmods.dev/badge/skills/xiqin/loom/loom-writing-plans.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 | $0.00039 | $0.02094 |
| Opus 5 | $0.00019 | $0.01047 |
| Sonnet 5 | $0.00008 | $0.00419 |
| Haiku 4.5 | $0.00004 | $0.00209 |
Grade A, and why
loom-writing-plans 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 12d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
实现计划拆解
触发条件
specs/<date+feature>/spec.md与specs/<date+feature>/requirements.json已存在并经用户确认。- 需要把 spec 拆为可独立验证的 task 文件。
输出
specs/<date+feature>/plan.md:摘要 + Task 概览。specs/<date+feature>/tasks/T1.md、T2.md...:每个 task 一个独立文件。specs/<date+feature>/traceability.json:REQ 与 behavior 到 task/test/evidence 的结构化追踪账本;planning 阶段至少写入 REQ/behavior 到 task 的初始映射,tests/evidence 可先为空并由 executing 补齐。specs/<date+feature>/handoffs/planning.json:规划阶段交接摘要。
产物根目录
本阶段的 specDir 是 specs/<date+feature>/。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、plan.md、tasks/、progress.md 或 handoffs/。
使用 assets/plan-template.md 和 assets/task-template.md 作为输出模板。
执行流程
- 读取
specs/<date+feature>/spec.md与specs/<date+feature>/requirements.json,提取功能点、接口、数据模型、边界场景、Requirement ID 和 behaviors。 - 读取
.loom/rules/constitution.md;如存在,读取.loom/contexts/subagent-context.md。 - 先规划文件结构:创建/修改哪些文件、每个文件职责、哪些文件一起变化。
- 按项目实际分层和依赖顺序拆 task:数据/模型 → 业务逻辑 → 接口/UI → 路由/配置 → 集成。
- 写
specs/<date+feature>/plan.md概览,再为每个 task 写完整specs/<date+feature>/tasks/TN.md。 - 写
specs/<date+feature>/traceability.json,把每个REQ-xxx及其REQ-xxx-Bnnbehavior 映射到负责的 task;planning 阶段不允许遗漏 behavior。 - 自检并运行自动校验。
- 写入
specs/<date+feature>/handoffs/planning.json,摘要说明 task 拆分、依赖顺序、关键接口约束、REQ/behavior 映射、并行/串行边界和主要产物。
如果 spec 涵盖多个独立子系统,建议拆成多个计划;每个计划都应能产出可工作、可测试的独立软件。
Task 粒度
- 每个 task 是一个可独立验证的交付物。
- 每个 task 包含层级、复杂度、依赖、涉及文件、Requirement ID 验收映射、TDD 步骤、测试说明。
- 每个 task 文件必须声明 YAML frontmatter,包含
owns(独占写入的文件/目录)、reads(只读依赖)、depends_on(前置 task)、requirements(覆盖的REQ-xxx)、behavior_ids(覆盖的REQ-xxx-Bnn)、complexity。这些字段驱动loom tasks命令的冲突检测、批次调度和 traceability 初始映射。 - 依赖必须无循环;有循环依赖时拆开或合并。
- 后续 task 使用的类型、方法签名和属性名必须与前序 task 匹配。
- 每个 spec Requirement ID 必须至少映射到一个 task;task 不得使用 spec 中不存在的 Requirement ID。
requirements.json中每个 behavior 必须至少映射到一个 task;task 不得使用requirements.json中不存在的behavior_ids。owns集合不得有交集:两个 task 不能同时 owns 同一文件/目录,否则不能并行执行。
What ships with it
3 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.
- 12d ago First seen · 141 lines · 39 tokens per session scan A e76d39191357
loom-writing-plans is a skill published in the GitHub repository xiqin/loom (5 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 2,094 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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…