Skip to content
Back to skills

Plan Milestone

ASecurity

Use ONLY when the user explicitly types `$plan-milestone <milestone-or-feature-idea>`. Do not trigger implicitly from generic phrasing.

  • 2 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 29, 2026
ai-agents

Works with

  • cli

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 plan-milestone --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Plan Milestone?

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

Security grade badge for Plan Milestone
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/kohj1018-plan-milestone/badge)](https://www.skillsdirectory.com/skills/kohj1018-plan-milestone)

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: plan-milestone
description: Use ONLY when the user explicitly types `$plan-milestone <milestone-or-feature-idea>`. Do not trigger implicitly from generic phrasing.
---

Source of truth: `.claude/skills/plan-milestone/SKILL.md` (skill 신설 근거: ADR-075 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 `/plan-milestone`·`/plan-workitem`·`/bootstrap-design`·`/discover-product` 등 표기는 Claude 슬래시 커맨드다. Codex에서는 `$plan-milestone` 등으로 읽고 사용자에게 안내한다 (예: 본문 "다음 단계: `/plan-workitem M2`" → Codex 응답에서는 "다음 단계: `$plan-workitem M2`"). Codex CLI는 `/`를 빌트인 슬래시 커맨드에 쓰므로 명시적 치환이 필요.

**Sub-agent parity**: 본문 R2의 architect·R5-2의 designer 단발 sub-call은 Claude `Agent` 도구 기능이다. Codex 서브에이전트는 GA이나 본 저장소가 Claude persona 위임을 Codex subagent로 아직 매핑하지 않아 메인 세션이 순차 단일 실행으로 직접 추론한다(degrade — SKILL.md 본문의 Codex 노트 정합).

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

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

Files in this skill

  • SKILL.md1.5 KB
  • agents/openai.yaml43 B

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.