agentmods.dev

judge-task-compiler

judge-task-compiler is a skill for Claude Code, Codex from JerryLookupU/klein-harness. It costs 66 tokens per session (731 once invoked), scanned A, original, MIT.

An orchestration guide for turning a complex request into a shared plan, a dependency graph, and separate worker tasks. A dependency graph shows which tasks must finish before others can start.

In plain words
What is it for?
Use it to break research or content work into object-specific tasks, freeze the required list and specifications, assign dependencies, and prepare worker instructions.
Why use it?
It reduces inconsistent assumptions and makes repeated work easier to divide, run in parallel, assemble, and verify.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 10repo 7mo ago A scan 66 tokens original MIT

Good fit Use it to break research or content work into object-specific tasks, freeze the required list and specifications, assign dependencies, and prepare worker instructions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jerrylookupu/klein-harness/judge-task-compiler
View source ↗ JerryLookupU/klein-harness
Install

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.

Any agent
npx skills add JerryLookupU/klein-harness --skill judge-task-compiler
Clone the repo
git clone --depth 1 https://github.com/JerryLookupU/klein-harness

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for judge-task-compiler

README.md
[![agentmods](https://agentmods.dev/badge/skills/jerrylookupu/klein-harness/judge-task-compiler/github.svg)](https://agentmods.dev/skills/jerrylookupu/klein-harness/judge-task-compiler)
Your own site
<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.

agentmods 80×15 button for judge-task-compiler

Your own site · 80×15
<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>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 731 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00066 $0.00731
Opus 5.5 $0.00026 $0.00292
Sonnet 5.5 $0.00013 $0.00146
Haiku 4.5 $0.00007 $0.00073

Measured 2mo ago against content hash cfd12ffc593c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 2mo 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.

skills/judge-task-compiler/SKILL.md · 91 lines

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 assemble
  • 5 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_outputs
  • extract_spec_constraints
  • synthesize_task_graph
  • validate_dispatch_contracts

优先顺序：

  1. 用 tool 收集和抽取结构化事实
  2. 用 skill 做蓝图收敛、fanout 和谱系判断
  3. 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_spec
  • task_list
  • dependency_graph
  • dispatch_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。

Files

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.

Changes

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.

  1. 2mo ago First seen · 91 lines · 66 tokens per session scan A cfd12ffc593c

Subscribe to this mod's changes

judge-task-compiler is a skill published in the GitHub repository JerryLookupU/klein-harness (10 stars, last pushed 7mo ago), licensed MIT. It adds 66 tokens to every session and 731 once invoked, about $0.0003 per session on Opus 5.5. 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.

Building agentsPlanning
Related

judge-task-compiler compared with skills from other repositories

judge-task-compiler next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
judge-task-compilerJerryLookupU/klein-harnessSkill107mo agoMITA66Claude Code, Codex
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99ktodayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79ktodayMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill314k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code