# Mission

> Break large coding tasks into milestones with validation gates and file-based state that survives context resets. Six commands cover the full lifecycle: plan the work, execute milestone-by-milestone, resume with fresh context after /clear, check progress, adjust the plan mid-flight, and run acceptance criteria. Built on Boyd's OODA loop — every milestone is an observe-orient-decide-act cycle, so the agent stays grounded in reality instead of drifting.

## Facts
- Page: https://tashan.sh/capability/plugin-ohong-agent-skills-mission
- tashan id: plugin:ohong/agent-skills/mission
- Source: https://github.com/ohong/agent-skills
- Type: plugin
- Category: other
- tashan score: 34.0 / 100
- Adoption: 11.0
- Upkeep: 57.0
- Freshness: 83.0
- Evidence coverage: 84% of the inputs this score can use
- Health: active
- Instruction depth: not yet graded
- GitHub stars: 1
- License: MIT
- Official: no

## Install

```sh
/plugin marketplace add anthropics/claude-plugins-community
/plugin install mission@claude-community
```

## Security audit
Not scanned. We audit npm-published capabilities; this one has no npm package we can resolve, or has not reached the queue. This is not a clean bill of health.

---
Measured 2026-09-13 by tashan (https://tashan.sh) from public evidence. Scorer s5.