What is harness-log-search-cskill?

A skill for searching Klein-Harness handoff and runtime logs. Klein-Harness is a system that coordinates coding workers and records their progress and results.

Use it to investigate verification failures, worker handoffs, runtime state, and operator-debugging questions.

It helps find the small amount of log evidence needed for debugging or resuming work without reading every worker transcript.

harness-log-search-cskill — Skill for Claude Code by JerryLookupU

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 harness-log-search-cskill

Clone the repo

git clone --depth 1 https://github.com/JerryLookupU/klein-harness

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jerrylookupu/klein-harness/harness-log-search-cskill/github.svg)](https://agentmods.dev/skills/jerrylookupu/klein-harness/harness-log-search-cskill)

Your own site

<a href="https://agentmods.dev/skills/jerrylookupu/klein-harness/harness-log-search-cskill"><img src="https://agentmods.dev/badge/skills/jerrylookupu/klein-harness/harness-log-search-cskill/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/jerrylookupu/klein-harness/harness-log-search-cskill"><img src="https://agentmods.dev/badge/skills/jerrylookupu/klein-harness/harness-log-search-cskill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 941 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.

Model	Per session	Once invoked
Fable 5.1	$0.00050	$0.00941
Opus 5.5	$0.00020	$0.00376
Sonnet 5.5	$0.00010	$0.00188
Haiku 4.5	$0.00005	$0.00094

Measured 2mo ago against content hash 0620f0241089, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

harness-log-search-cskill 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/harness-log-search-cskill/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

This Skill Is For

这个 skill 用于在不广播完整 worker transcript 的前提下，搜索 .harness 日志面。

默认目标：

先读热路径状态和 compact logs
只在 --detail 或证据不足时回落到 raw runner logs

Use When

适用于：

resume 前需要恢复 handoff / verify / recent failure 上下文
要做 operator debug 或 RCA
要围绕 verify、handoff、runtime state 做定向日志检索
需要给 Codex 一个“先 compact、后 raw fallback”的日志读取纪律

Do Not Use When

不适用于：

普通实现任务一开始就扫日志
没有明确日志诉求时默认扫描 raw runner logs
为了省事贴整段 transcript 给下游 agent

Expected Effects

使用这个 skill 后，Codex 应该：

先读热状态与 compact logs
把日志检索结果压缩成 one-screen summary
返回 blockers / risks / verification notes / evidence refs
raw logs 仅返回相关窗口，不返回整段 transcript

Retrieval Order

默认读取顺序：

.harness/state/current.json
.harness/state/runtime.json
.harness/state/request-summary.json
.harness/state/lineage-index.json
.harness/state/log-index.json
.harness/log-<taskId>.md
.harness/state/runner-logs/<taskId>.log 仅用于定向细节

不要默认把所有 raw logs 都扫一遍。

Preferred Command Surface

优先使用：

.harness/bin/harness-log-search . --task-id T-003
.harness/bin/harness-log-search . --keyword verify --detail
.harness/bin/harness-query logs . --text
.harness/bin/harness-query log . T-003 --detail --text

What To Return

优先返回：

one-screen summary
cross-worker relevant facts
blockers / risks
verification notes
evidence refs

如果需要 raw evidence，只返回相关窗口，不要贴完整 transcript。

Canonical Runtime Mapping

这个 skill 的真正落点不在这里，而在：

internal/route/gate.go
- 负责把 resume / log-search / evidence retrieval 信号变成 policy_* tags
internal/orchestration/defaults.go
- 负责把 compact-log-first 纪律写入 methodology / execution loop / constraints
internal/worker/manifest.go
- 负责把日志读取顺序和 raw fallback 规则注入给 Codex

这份 SKILL.md 是给 Codex 的入口说明，不是 runtime authority。

Minimal Read Order / Inputs

Codex 在真正执行前，最小读取面应优先是：

.harness/state/current.json
.harness/state/runtime.json
.harness/state/request-summary.json
.harness/state/lineage-index.json
.harness/state/log-index.json
.harness/log-<taskId>.md
只在 detail fallback 时读 .harness/state/runner-logs/<taskId>.log

Read the full file on GitHub · 119 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.

2mo ago First seen · 119 lines · 50 tokens per session scan A 0620f0241089

Subscribe to this mod's changes

harness-log-search-cskill is a skill published in the GitHub repository JerryLookupU/klein-harness (10 stars, last pushed 7mo ago), licensed MIT. It adds 50 tokens to every session and 941 once invoked, about $0.0002 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.

Debugging

harness-log-search-cskill next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
harness-log-search-cskillJerryLookupU/klein-harness	Skill	10	7mo ago	MIT	A	50	Claude Code
systematic-debuggingopen-metadata/OpenMetadata	Skill	16k	today	Apache-2.0	A	37	Claude Code
log-error-digestzebbern/claude-code-guide	Skill	4.7k	today	MIT	A	71	Claude Code, Codex
cwv-optimizeradobe/skills	Skill	319	today	Apache-2.0	A	112	Claude Code
ci-fixersipyourdrink-ltd/bernstein	Skill	1.2k	today	Apache-2.0	A	15	Claude Code, Codex
diagnosing-missing-recordingsPostHog/posthog	Skill	41k	today	none	A	76	Claude Code, Codex
loop-engineeringhuytieu/COG-second-brain	Skill	1.3k	15d ago	MIT	A	63	Claude Code