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 JerryLookupU/klein-harness --skill qiushi-executiongit clone --depth 1 https://github.com/JerryLookupU/klein-harnessWrote 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/jerrylookupu/klein-harness/qiushi-execution)<a href="https://agentmods.dev/skills/jerrylookupu/klein-harness/qiushi-execution"><img src="https://agentmods.dev/badge/skills/jerrylookupu/klein-harness/qiushi-execution/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/jerrylookupu/klein-harness/qiushi-execution"><img src="https://agentmods.dev/badge/skills/jerrylookupu/klein-harness/qiushi-execution.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 | $0.00086 | $0.01403 |
| Opus 5 | $0.00043 | $0.00701 |
| Sonnet 5 | $0.00017 | $0.00281 |
| Haiku 4.5 | $0.00009 | $0.00140 |
Grade A, and why
qiushi-execution 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 10d 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Qiushi Execution
这个 skill 为 Klein-Harness 提供一套轻量、可执行的方法纪律,不新增新的 runtime 实体,也不替代现有的 route、b3ehive packet synthesis、dispatch、worker、verify 链路。
目标只有一个:
- 让判断更贴事实
- 让规划更聚焦
- 让执行更闭环
Use When
适用于:
- 任务复杂,但事实不足
- 方向很多,需要先收敛主线
- 已经执行过,但 verify / closeout 还没闭环
- 任务完成状态与 evidence 不一致
- 需要把 worker 行为收得更稳
Do Not Use When
不适用于:
- 把它当成新的 runtime
- 用它替代 route / dispatch / verify / gate
- 用它做大段方法论叙事而不进入执行
Expected Effects
使用这个 skill 后,Codex 应该:
- 调查优先,而不是凭经验直接改
- 一次只推进一个 bounded slice
- 用命令 / 文件 / artifact 证据证明完成
- 在 closeout 里诚实写清风险和未完成项
核心纪律
- 先事实,后判断
- 在证据不足、上下文不清、仓库陌生时,先调查,再下结论。
- 不把猜测、经验或偏好当成事实。
- 先聚焦,后扩展
- 同一轮只解决一个最有杠杆的核心问题。
- 不把多个目标揉成一个模糊的大任务。
- 先实践,后宣布完成
- 方案必须经过执行、验证或可审计证据的检验。
- 没有 artifact、verify、日志,不算完成。
- 先复盘,后收口
- 收口前必须明确本轮做了什么、验证了什么、还剩什么风险。
- 对失败和偏差要能诚实写进 handoff 或 review。
与 Klein 运行时的映射
Route
- 证据不足时优先调查,不急于分发大任务。
- 在多个方向里选一个主攻方向,避免同时散开。
- 当存在速度、风险、范围、可验证性冲突时,优先选可验证、可回滚、边界清晰的路线。
B3Ehive Packet Synthesis
- planner A 更关注边界和结构。
- planner B 更关注交付切片和顺序。
- planner C 更关注风险、验证和回滚。
- judge 不是做平均,而是选一个最适合当前仓库和当前证据的方案。
Worker Execution
- 先读 dispatch ticket、worker-spec、planning trace。
- 然后尽快进入受控执行,不做无休止的二次规划。
- 每次改动都要朝验证闭环推进。
Verify / Handoff
- verify 必须记录命令、结果、证据路径。
- handoff 必须说明已完成、未完成、风险和下一步。
- 如果 evidence 不完整,宁可阻断 closeout,也不要假完成。
适用信号
当出现这些信号时,优先遵循这套纪律:
- 任务复杂,但事实不足
- 方向很多,但注意力有限
- 执行已经发生,但验证还没闭环
- 任务完成状态和底层 evidence 不一致
- 需要把 planning 和 worker 行为收得更稳
禁止事项
- 不新增平行控制面
- 不把方法论做成新的 task ledger 实体
- 不用口头总结替代 verify 证据
- 不在执行阶段无限扩读文档来逃避落地
使用方式
把它当成 Klein 的工作纪律,而不是单独的 runtime。
一句话记忆:
调查优先 -> 聚焦主线 -> 小步执行 -> 证据验证 -> 诚实复盘
Canonical Runtime Mapping
这份 SKILL.md 的真正 runtime 落点是:
internal/route/gate.go- 通过
policy_bug_rca_first、policy_resume_state_first等 reason code 激活不同 discipline
- 通过
internal/orchestration/defaults.go- 通过
MethodologyContract、ExecutionLoopContract、ConstraintSystem结构化表达这套纪律
- 通过
internal/worker/manifest.go- 把这套纪律写进 dispatch ticket、worker-spec、worker prompt
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.
- 10d ago First seen · 166 lines · 86 tokens per session scan A 00fa3e614e0d
qiushi-execution is a skill published in the GitHub repository JerryLookupU/klein-harness (11 stars, last pushed 5mo ago), licensed MIT. It adds 86 tokens to every session and 1,403 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…
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…
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…