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 judge-task-compilergit 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/judge-task-compiler)<a href="https://agentmods.dev/skills/jerrylookupu/klein-harness/judge-task-compiler"><img src="https://agentmods.dev/badge/skills/jerrylookupu/klein-harness/judge-task-compiler/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/judge-task-compiler"><img src="https://agentmods.dev/badge/skills/jerrylookupu/klein-harness/judge-task-compiler.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 | $0.00066 | $0.00731 |
| Opus 5 | $0.00033 | $0.00365 |
| Sonnet 5 | $0.00013 | $0.00146 |
| Haiku 4.5 | $0.00007 | $0.00073 |
Grade A, and why
judge-task-compiler 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.
What it actually says
This Skill Is For
这个 skill 服务于中枢编排节点，不服务于普通 worker。
它负责把上游 planner、swarm agent、用户初始输入和已有产物，收敛成一份可执行的 task graph。
默认目标：
- 先定共享
spec - 再定
task list - 再定
dependency lineage - 最后才交给 worker 执行
Core Capabilities
1. 蓝图拆解
先把需求压成共享蓝图，不要急着出 worker task：
- 明确目标、非目标、交付物
- 冻结对象集合或名单
- 冻结文件合同、字段模板、长度要求、来源策略
- 把共享信息放进
packet.sharedContext
2. Swarm 组装
识别哪些任务是“同类、同模板、不同对象”的 fanout 任务。
默认规则：
- 同类型重复任务，优先一对象一 worker
- worker 任务主体只保留当前对象的差异
- 共用背景、约束、SPEC 不要重复散落到每个 worker 自己推断
例子：
20 位语言学家资料->20 个对象 worker + 1 个 assemble5 个角色卡片生成->5 个对象 worker + 1 个 assemble
3. 谱系编排
把任务整理成 DAG，而不是平铺清单。
至少回答：
- 哪些任务要先跑
- 哪些任务可以并行
- 哪些任务依赖冻结名单或共享 spec
- 哪些任务负责 assemble / verify / closeout
Working Rules
- 先读用户初始输入与 planner outputs，再决定 fanout
- 当 roster 未冻结时，不要提前生成实名 worker slices
- 对 repeated-object 请求，先生成
冻结名单与分片规格之类的 orchestration slice - roster 一旦冻结，重新物化
executionTasks - worker handoff 必须是纯文字分层，不要把整包 JSON 原样塞给 worker
Tool-First Fallback
当 skill 判断不稳定、对象识别含糊、或需要结构化校验时，不要硬猜。
改用 references/tool-contracts.md 里的 tool contracts：
collect_b3ehive_outputsextract_spec_constraintssynthesize_task_graphvalidate_dispatch_contracts
优先顺序：
- 用 tool 收集和抽取结构化事实
- 用 skill 做蓝图收敛、fanout 和谱系判断
- 用 tool 校验 dispatch contract 是否足够原子、清晰、可执行
Output Standard
这个 skill 的直接产物应该能映射到：
shared_spectask_listdependency_graphdispatch_contracts
如果 roster 还没冻结，允许只输出第一阶段 orchestrator slice，并明确 orchestration expansion pending。
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.
- 10d ago First seen · 91 lines · 66 tokens per session scan A cfd12ffc593c
judge-task-compiler is a skill published in the GitHub repository JerryLookupU/klein-harness (11 stars, last pushed 5mo ago), licensed MIT. It adds 66 tokens to every session and 731 once invoked, about $0.0003 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…