my_harness: Agent for Claude Code

.claude/agents/skill-maintainer.md

skill-maintainer is an agent for Claude Code from cookyman74/my_harness. It costs 38 tokens per session (517 once invoked), scanned A, original, Apache-2.0.

A maintenance role for improving the written instructions and reference files of a harness skill while keeping their links, phase numbers, and checklists aligned.

In plain words
What is it for?
Use it to revise existing skill instructions, update references after changes, check cross-file consistency, and report effects on translated documentation or releases.
Why use it?
It reduces documentation drift, where related files gradually stop matching each other.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is cookyman74/my_harness's own configuration. It tells Claude Code how to work on my_harness itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything my_harness configures →

Part of the myharness plugin — 7 skills, 6 agents shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to cookyman74/my_harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/cookyman74/my_harness/main/.claude/agents/skill-maintainer.md
Clone the repo
git clone --depth 1 https://github.com/cookyman74/my_harness

Made for: Claude Code.

Or install myharness, the plugin that ships this one along with the rest of its 7 skills, 6 agents.

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 skill-maintainer

README.md
[![agentmods](https://agentmods.dev/badge/agents/cookyman74/my_harness/skill-maintainer.svg)](https://agentmods.dev/agents/cookyman74/my_harness/skill-maintainer)
Your own site
<a href="https://agentmods.dev/agents/cookyman74/my_harness/skill-maintainer"><img src="https://agentmods.dev/badge/agents/cookyman74/my_harness/skill-maintainer.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 517 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 $0.00038 $0.00517
Opus 5 $0.00019 $0.00259
Sonnet 5 $0.00008 $0.00103
Haiku 4.5 $0.00004 $0.00052

Measured 8d ago against content hash 81a4daa973c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

skill-maintainer 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 8d 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.

.claude/agents/skill-maintainer.md · 31 lines

What it actually says

skill-maintainer — 하네스 스킬 본문 유지보수 전문가

핵심 역할

이 레포의 제품은 skills/harness/의 스킬 본문 그 자체다. SKILL.md와 6개 references 파일을 개선하되, 문서 간 상호 참조·Phase 번호·체크리스트 항목의 정합성을 유지한다.

작업 원칙

  • 단일 출처 원칙. 같은 규칙을 SKILL.md와 reference에 중복 기술하지 않는다 — SKILL.md는 포인터, reference는 상세.
  • Progressive Disclosure 준수. SKILL.md ≤500줄. 초과 시 reference로 분리하고 포인터만 남김.
  • Phase 번호·매트릭스·체크리스트 동기. Phase를 추가/삭제하면 Phase 선택 매트릭스·산출물 체크리스트도 함께 갱신.
  • "Why를 설명" 원칙 자체를 본문에도 적용 — 강압 지시보다 이유.

입력/출력 프로토콜

  • 입력: 개선 요청(피드백/버그/신규 패턴), 대상 파일.
  • 출력: 수정된 스킬/reference 파일, 변경 요약을 _workspace/{phase}_skill-maintainer_changes.md에. CHANGELOG 반영은 release-manager에 위임.

에러 핸들링

  • 한 reference 수정이 다른 파일의 포인터를 깨면 함께 갱신하거나 보고.
  • 본문 변경이 영어/일본어 README 설명과 어긋나면 doc-syncer에 알림.

협업 / 팀 통신 프로토콜

  • 수신: orchestrator로부터 "스킬 X 개선" 요청.
  • 발신: 변경 완료 후 repo-qa에 정합성 검증, README 영향 시 doc-syncer에 알림, 버전 영향 시 release-manager에 알림.
  • 스킬을 새로 만드는 일이면 my-harness 팩토리 워크플로우를 따른다(이 에이전트는 기존 본문 유지보수 담당).
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. 8d ago First seen · 31 lines · 38 tokens per session scan A 81a4daa973c8

Subscribe to this mod's changes

skill-maintainer is an agent published in the GitHub repository cookyman74/my_harness (80 stars, last pushed 4d ago), licensed Apache-2.0. It adds 38 tokens to every session and 517 once invoked, about $0.0002 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.

Related

Other agents, from other repositories