Repair Acceptance

Name: Repair Acceptance
Author: kohj1018

ASecurity

Use ONLY when the user explicitly types `$repair-acceptance <milestone-id>`. Do not trigger implicitly from generic phrasing.

2 stars
0 votes
0 copies
2 views
Added September 29, 2026

ai-agents

Security analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned September 29, 2026

npx -y skills add kohj1018/agentic-dev-harness --skill repair-acceptance --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Repair Acceptance?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Repair Acceptance

[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/kohj1018-repair-acceptance/badge)](https://www.skillsdirectory.com/skills/kohj1018-repair-acceptance)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro

SKILL.md

---
name: repair-acceptance
description: Use ONLY when the user explicitly types `$repair-acceptance <milestone-id>`. Do not trigger implicitly from generic phrasing.
---

Source of truth: `.claude/skills/repair-acceptance/SKILL.md` (skill 신설 근거: ADR-066 D4). Read it and follow the workflow.

Treat all frontmatter keys other than `name` and `description` (e.g., `agent:`, `disable-model-invocation:`, `allowed-tools:`, `context:`, `argument-hint:`, `model:`, `effort:`) as Claude-only and ignore them — execute locally in Codex.

**Slash command translation**: 본문 안의 `/repair-acceptance` 표기는 Claude 슬래시 커맨드다. Codex에서는 `$repair-acceptance`로 읽고 사용자에게 안내한다 (예: 본문 "다음 단계: `/accept-milestone M1`" → Codex 응답에서는 "다음 단계: `$accept-milestone M1`").

**Codex degrade**: 서브에이전트 위임 없이 메인 세션이 순차 단일 실행한다(판정 결과 동일).

Preserve all repo policies from `AGENTS.md` and `docs/`.

If the source path no longer exists, this wrapper is stale — see ADR-010.