agentloop-corelisted

# agentloop Core ## Workflow 1. Write goal + done-definition + verify command. 2. **If the map is fuzzy, discover first** (`/unknowns` / finding-unknowns pack) before spending a build loop. 3. Choose mode: single | pev | warroom | swarm (smallest first). 4. Load only the skills you need — **compose for quality**, don’t spray workers. 5. For craft/launch work, prefer `quality-compose` over `subagent-swarm`. 6. Execute with narration diet. Keep `implementation-notes` when working a plan. 7. Run `ship-gate` before claiming done. Optionally `change-quiz` before merge. 8. Final message: outcome first, then details. ## Discovery pack (before) | Need | Skill | |---|---| | Unfamiliar area / domain | `blindspot-pass` | | Taste you can’t verbalize | `brainstorm-prototypes` | | Ambiguity remains | `interview-me` | | “Like that” is the spec | `reference-hunt` | | Lock decisions | `implementation-plan` | | During a planned build | `implementation-notes` | | Buy-in doc | `pitch-packager` | | Before merge | `change-quiz` | | Bloated agent context | `context-audit` | | Agent-facing tools | `agent-interface-design` | | Oversized skill/spec | `progressive-disclosure` | ## Craft pack (on demand) | Need | Skills | |---|---| | Kill generic AI output | `no-ai-slop` | | Sound human | `humanise` | | Personality dial | `optional-ponytail` (off by default) | | Screen review | `ui-ux-audit` | | Go-live readiness | `deployment-audit` | | Public copy | `seo-copywriting` | | Contrast (visual + steel