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 agentmods add skills/yibie/spec-agents.md/donpx skills add yibie/SPEC-AGENTS.md --skill dogit clone --depth 1 https://github.com/yibie/SPEC-AGENTS.mdWrote 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/yibie/spec-agents.md/do)<a href="https://agentmods.dev/skills/yibie/spec-agents.md/do"><img src="https://agentmods.dev/badge/skills/yibie/spec-agents.md/do.svg" alt="Measured on agentmods" 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 | $0.00049 | $0.01632 |
| Opus 5 | $0.00024 | $0.00816 |
| Sonnet 5 | $0.00010 | $0.00326 |
| Haiku 4.5 | $0.00005 | $0.00163 |
Grade A, and why
do 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 yesterday.
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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Do
只执行当前允许的一个切片,不重新打开已经确认的设计。
开始前
先确定走的是哪一条路径,两条的前置条件不同。
SPEC 路径(经过 capture 与 arrange)
读取 AGENTS.md、.spec-agents/doctrine/docs/WORKFLOW.md、CONTEXT.md、项目
.spec-agents/state/KERNEL.md(若存在)、.spec-agents/state/STATUS.md、相关 SPEC.md、一个目标 Slice 和必要的
Protocol、Runbook、Lesson。确认:
- Slice 状态是
ready或已明确授权的doing; - 所有
blocked_by已完成; - SPEC 没有
stale; - Slice 未声明
writer:,或声明的就是do; - Slice 的
authority:已对照过 Kernel 的 Architecture boundaries(见下); - 当前代码、测试和配置与任务范围一致。
短路径(plan 直接给出 approve)
这条路径上没有 SPEC 也没有 Slice。不要为它创建一个 —— 那正是这套流程
拒绝的 ticket。读取 AGENTS.md、.spec-agents/doctrine/docs/WORKFLOW.md、
CONTEXT.md、项目 .spec-agents/state/KERNEL.md(若存在)、.spec-agents/state/STATUS.md 和必要的 Protocol、
Runbook、Lesson。确认:
plan给出的结果允许直接执行:approve;或已获用户明确授权的plan-only; 或compatible revise且该替代方案在当前上下文内可完成;- 它交出的「保持不变的契约」和那句验收都已知;
- 工作仍然可以在当前上下文内完成。
执行中发现它不再是单上下文的工作,停下回到 plan,不要就地编一个 SPEC。
两条路径都适用:先对权威落点
动手前把这次要写的位置,对照项目 .spec-agents/state/KERNEL.md 的 Architecture boundaries
(权威落点地图)。短路径上没有 Slice,就直接拿打算落笔的模块去对。两种结果:
- 图上有这条规则,而目标位置不是它 —— 停下回到
plan。要么落点不对, 要么地图该改,两者都不是do能自己决定的。 - 图不存在,或图上没有覆盖这条规则的条目 —— 不要停。记下打算落笔的
位置,产出一个
semantic发现交给plan,然后继续执行。
第二种情况刻意不阻断:存量 Kernel 本来就不要求回填这张图(见 .spec-agents/doctrine/START.md),
把地图缺失变成硬停会让合规项目动不了,而一条动不了的规则一定会被绕过。缺失
是 Kernel 的缺口,不是这次工作的缺陷 —— 交给拥有 Kernel 变更的那道门去补。
do 从不修改这张图。在症状出现的那一层顺手加分支,是功能生效但生效在错误
位置的主要方式。
执行
- 先追踪真实调用链和既有 seam,选择最小可行改动。
- 对有分支、循环、解析、金钱或安全影响的逻辑,留下一个可运行的检查。
- 保持 Action Contract、不变量和数据契约不变,除非
plan已批准兼容修订。 - 运行任务要求的测试、类型检查、静态检查或最小手工验证。
- 把当前 Slice 留在
doing并写下验证摘要,供check、learn使用; 短路径上没有 Slice 可更新,跳过这一步;保持evidence_ref为空。do不关闭 Slice ——done与evidence_ref由learn在check之后一起写入。 - 不写根目录 Evidence,也不回写 Evidence ID。
如果仓库存在 .jj/,本地版本操作遵循 JJ:用 jj new/jj edit 开始上下文、
用 jj describe 记录意图、用 jj status/jj diff 检查。把当前 JJ Change
ID 写入 Slice 或交接摘要时,仍然以 SPEC 与 Slice 作为语义来源;不要用
git add、git commit 或 git stash 模拟 JJ。没有 .jj/ 时才沿用项目现有
Git 工作流;不要在 do 中自动初始化或 push。
What ships with it
1 file 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.
- yesterday Changed · +3 lines 8e12dd297a21
- 6d ago First seen · 104 lines · 49 tokens per session scan A 16973cebed88
do is a skill published in the GitHub repository yibie/SPEC-AGENTS.md (126 stars, last pushed 4d ago), licensed MIT. It adds 49 tokens to every session and 1,632 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 2026-08-30.
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…
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…
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…
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…