jit-harness

jit-harness is a skill for Claude Code, Codex from JacksonTai2007/cc-unlock. It costs 150 tokens per session (2,172 once invoked), scanned A, original, MIT.

A task-execution system that builds a step-by-step working plan for complex jobs, checks clear success conditions, and adjusts its approach when steps fail.

In plain words
What is it for?
Use it for involved coding, debugging, data work, research, refactoring, migrations, or build and deployment tasks.
Why use it?
It gives multi-step work a defined goal and recovery process instead of relying on an unstructured sequence of actions.

Skill for Claude CodeCodex

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

Good fit Use it for involved coding, debugging, data work, research, refactoring, migrations, or build and deployment tasks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jacksontai2007/cc-unlock/jit-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 JacksonTai2007/cc-unlock --skill jit-harness
Clone the repo
git clone --depth 1 https://github.com/JacksonTai2007/cc-unlock

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 jit-harness

README.md
[![agentmods](https://agentmods.dev/badge/skills/jacksontai2007/cc-unlock/jit-harness/github.svg)](https://agentmods.dev/skills/jacksontai2007/cc-unlock/jit-harness)
Your own site
<a href="https://agentmods.dev/skills/jacksontai2007/cc-unlock/jit-harness"><img src="https://agentmods.dev/badge/skills/jacksontai2007/cc-unlock/jit-harness/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 jit-harness

Your own site · 80×15
<a href="https://agentmods.dev/skills/jacksontai2007/cc-unlock/jit-harness"><img src="https://agentmods.dev/badge/skills/jacksontai2007/cc-unlock/jit-harness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 150 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,172 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00150 $0.02172
Opus 5 $0.00075 $0.01086
Sonnet 5 $0.00030 $0.00434
Haiku 4.5 $0.00015 $0.00217

Measured 3d ago against content hash 91ecfcda10c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

jit-harness 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 3d 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.

cc-unlock-files/skill-bundle/jit-harness/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

JIT-Harness — 即时 Harness 合成与自我进化引擎

面对任何非平凡、多步、目标可判定的任务时,用这套引擎组织执行。核心思想:harness intelligence —— 不套固定的通用 scaffold,而是即时合成一套贴合当前任务的执行 harness,运行中自我进化。scaffold 设计是独立于模型能力的增益维度:同样的模型,harness 装得对,收敛更快、工具调用更省、成功率更高。

什么时候用它:任务需要 3 个以上有依赖的步骤、有明确的"做成了没有"的判据、且中途可能失败需要调整——编码实现、复杂 bug 定位、数据清洗/迁移、代码库重构、多源研究调查、CI/构建/部署流水线、逆向与安全研究(领域专用装配见 sec-forge skill)。单步问答、纯查询、创意写作不需要。

Harness 协议 — 四模块(M / P / A / F)

一个 harness = 这四个模块针对当前任务的一次具体装配。任务不同,装配不同;运行中按需重装。

  • M — Memory(记忆 / 上下文):维护任务历史、中间产物、有效模式归档(harness archive)。把已验证的手法(一段能跑通的查询、一个正确的配置片段、一处关键根因、一个可复用的脚手架)沉淀下来,跨阶段、跨同类子任务复用,不重复踩坑。
  • P — Planning(规划):合成/澄清目标,把任务分解为带交付物的阶段。依赖简单 → 线性链;依赖交叉但可并行 → DAG;某子目标本身又是一个完整任务 → 递归委派(开一层子 loop)。
  • A — Action(执行):逐步执行并更新状态。每步后对照 success oracle 评估是否命中。走命中 oracle 的最省路径——不做冗余工具调用,不为"稳妥"重复已成功的步骤。
  • F — Capability(能力编排):为每个阶段选择并编排合适的工具 / 命令 / 库 / 子技能。按任务需要装配,不预设一套万能工具。

Success Oracle —— 先定判据,再动手

执行前先明确怎样算这个阶段/任务成功,写成可判定的判据,而非模糊的"做好了":

  • 测试通过 / 构建成功 / 特定输出出现 / 数值达标 / 幂等重跑一致 / 某断言为真 / 复现从干净状态跑通。
  • oracle 是修复循环的锚:每次执行后拿它对照,命中才算过,不靠感觉。
  • 判据不清的任务,第一步就是把判据定清楚(和用户对齐或从上下文合成),不带着模糊判据往下冲。

三阶段 Harness 生命周期

Stage I — 定制(Customization)

即时合成贴合任务的 harness:

  1. 锁定目标 + 定义 success oracle(M + P)。目标明确 → 直接用;不明确 → 从上下文合成最优目标,不空问"你的目标是什么"。先于执行把成功判据定下来。
  2. 能力装配(F):根据任务性质选路线与工具链(该用哪个库/命令/子技能/分析手段),不问用户"用哪个"。
  3. 分解(P):拆 3-5 个带交付物的阶段,依赖排成 DAG,多跳子目标递归委派。清单列完立即进第一阶段,不问"要开始吗"。

Stage II — 修复(Repair,有界)

逐阶段执行(A),每阶段完成后对照 success oracle 评估:

执行阶段 N(A)
    ↓
对照 success oracle — 命中?
    ↓ 是 → 有效手法归档进 M → 阶段 N+1
    ↓ 否 → 有界修复(bounded repair):
         分析失败根因(不猜、看实际报错/实际输出)
         → 同一 harness 上原地修复(调参 / 换工具 / 改代码 / 改输入)
         → 重跑 → 再对照 oracle
         → 原地修复最多 2 轮

有界修复原则:每次失败先定位根因,不重复同一策略;修复是有界的,同一 harness 上原地修最多 2 轮;2 轮仍不收敛 → 不再原地修,进 Stage III 改结构。

Stage III — 进化(Evolution)

原地修复触顶 → 改 harness 结构本身,而非继续调参:

  • 换模块装配:换能力路线(F,如换库/换方法)/ 换分解方式(P,如线性改 DAG、单跳改递归委派把大阶段拆成子 loop)/ 换执行策略(A,如静态推断改实测、猜改成加日志复现)。
  • 归档沉淀:进化出的有效手法写进 M(harness archive),后续阶段和同类子任务直接复用——手法累积,越往后越快。
  • 结构性改造仍连续 2 次不通 → 停下,说清卡在哪 + 给几个选项,不空转。

Read the full file on GitHub · 95 lines

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. 3d ago First seen · 95 lines · 150 tokens per session scan A 91ecfcda10c8

Subscribe to this mod's changes

jit-harness is a skill published in the GitHub repository JacksonTai2007/cc-unlock (151 stars, last pushed 4d ago), licensed MIT. It adds 150 tokens to every session and 2,172 once invoked, about $0.0007 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 2026-09-06.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 83 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens