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/plannpx skills add yibie/SPEC-AGENTS.md --skill plangit 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/plan)<a href="https://agentmods.dev/skills/yibie/spec-agents.md/plan"><img src="https://agentmods.dev/badge/skills/yibie/spec-agents.md/plan.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 | $0.00084 | $0.01518 |
| Opus 5 | $0.00042 | $0.00759 |
| Sonnet 5 | $0.00017 | $0.00304 |
| Haiku 4.5 | $0.00008 | $0.00152 |
Grade A, and why
plan 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 today.
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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan
把“要不要改、改什么、改到哪里”为止先说清楚,再允许后续动作。
读取
- 读取
AGENTS.md、.spec-agents/doctrine/docs/WORKFLOW.md、CONTEXT.md、.spec-agents/state/STATUS.md; 项目有.spec-agents/state/KERNEL.md时一并读取。 - 只有当前判断需要历史依据、风险分类或回归对比时,才读取
.spec-agents/state/EVIDENCE.md或.spec-agents/archive/。 - 查代码、调用方、测试和配置来回答事实;不要把可以查到的事实丢给用户回答。
质询
按设计树分轮工作:
- 先确认需求、未改变的基线和“不改会怎样”。
- 只问当前前置条件已经确定的问题;每轮完整询问当前 frontier,再等待用户回答。
- 区分事实与决定:事实由 agent 查,取舍由用户确认。
- 继续到没有未决分支,不因一个看似合理的解释提前结束。
.spec-agents/state/STATUS.md已有活跃 SPEC 时,检查新工作的 scope 是否与它们相交。相交就在 这一轮重新划分边界,不要留到执行时用隔离工作副本掩盖。- 确认工作要写的文件各归哪个动作。被管项目中安装进来的 doctrine 不属于任何 动作,需要改它说明这项工作属于上游仓库,不属于本项目。
保持一份候选记录:
kind: add | refine | rename | split | merge | retire | plan-only
need:
unchanged_baseline:
old_definition:
new_definition:
knowledge_class: semantic | decision | protocol | runbook | lesson | state
scope:
applies_when:
identity_and_relations:
lifecycle_and_invariants:
action_contracts:
kernel_status: absent | K1-bootstrap | enacted | stale | contradicted
kernel_promotion: bootstrap | revise | supersede | none
compatibility: no-change | compatible | breaking | unresolved
mapping_and_migration:
verification:
decision: no-change | revise | approve | reject | unresolved
路由
用户确认共享理解后,只选择一个结果:
no-change:停止,不创建 SPEC、不改代码。plan-only:输出边界明确的计划,等待执行授权。获得授权后:单上下文可完成的 交给do(do的短路径接受已授权的plan-only),跨上下文的交给capture。approve:语义不变且当前上下文内可完成,交给do。两个条件都要满足; 语义不变但一个上下文完不成的工作走capture——它需要的是可交接的契约, 不是语义门。大小不是判据:Change Boundary 已经写明一个很小的 diff 也可能是语义变化。这条路径不产生 SPEC 也不产生 Slice。compatible revise:明确一个兼容替代方案,保留旧不变量和数据契约。跨上下文的 交给capture,单上下文可完成的交给do(do的短路径接受它)。breaking:必须确定迁移方案,由capture写进 SPEC,不能伪装成兼容修改。 ADR 由learn在收尾时写,和其它长期记录一样——此刻还没有任何东西被 验证过,learn的触发条件尚未满足(见docs/adr/0004)。reject/unresolved:停止;只有用户需要长期记忆时才交给learn留痕。
approve 必须交出什么
短路径不产生 SPEC 也不产生 Slice,所以 plan 必须在路由时口头交出两样东西,
否则 do 无从开始、check 无从比对:
- 保持不变的契约 ——
do不得扰动的不变量、接口或数据契约; - 怎么算完 —— 一句可验证的验收,
check就对着它比。
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.
- today Changed 97e4ae3bbc82
- 6d ago First seen · 108 lines · 84 tokens per session scan A be6d94064983
plan is a skill published in the GitHub repository yibie/SPEC-AGENTS.md (126 stars, last pushed 4d ago), licensed MIT. It adds 84 tokens to every session and 1,518 once invoked, about $0.0004 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…
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…