kaimingwan/oh-my-kiro/omk-agent

Trigger Examples

• "@agent 所有 JSON 操作必须用 jq"
• "add this as a permanent rule"
• "enforce: never skip tests"
• "把这个原则写进规则"
• "@agent submodule 修改必须走 worktree"

Agent — Distill Top-Level Principle

Capture a principle into knowledge/rules.md as a staged rule.

Input

$ARGUMENTS

Process

1. If no input provided, ask user: "What principle should I capture?"
2. Extract: trigger scenario + DO/DON'T action + keywords
3. Check dedup: grep -iw keywords in knowledge/rules.md and knowledge/episodes.md

• Already in rules → tell user, skip
• Already in episodes with same meaning → tell user, suggest upgrading to rule

1. Determine severity: 🔴 (critical, always inject) or 🟡 (relevant, keyword-matched)
2. Find or create matching section header ## [keyword1,keyword2] in knowledge/rules.md
3. Append rule under that section, format: 🔴 N. SUMMARY or 🟡 N. SUMMARY
4. Cap: max 5 rules per section, max 30 rules total. Warn if approaching limit.
5. Output: 📝 Captured → rules.md: 'SUMMARY'

Rules

• Summary must contain actionable DO/DON'T, not narrative
• Keywords: 1-3 english technical terms, ≥4 chars each, comma-separated
• Default severity: 🟡 (only use 🔴 for principles that should apply to EVERY conversation)