# Delegation Pack

> Ready-to-send task files for Saravana, Codex, Windsurf, and Cursor.
> Use these files when assigning bounded ecosystem work to another coding agent.

---

## Current Delegation Set

- [`saravana/COORDINATION.md`](/Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/saravana/COORDINATION.md)
- [`codex/PHASE1_INTEGRATION_REVIEW.md`](/Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/codex/PHASE1_INTEGRATION_REVIEW.md)
- [`windsurf/NOTELETT_PHASE1_VERIFICATION.md`](/Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/windsurf/NOTELETT_PHASE1_VERIFICATION.md)
- [`cursor/MINDLYST_PHASE1_VERIFICATION.md`](/Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/cursor/MINDLYST_PHASE1_VERIFICATION.md)
- [`TWO_WAY_COMMUNICATION_REFACTOR_PLAN.md`](/Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/TWO_WAY_COMMUNICATION_REFACTOR_PLAN.md)
  - review this before refactoring the participant folders into the 3-file communication loop

---

## Standard Launcher Pattern

Give an agent a one-liner in this form:

```bash
git pull origin main && read the task file at <absolute-path> and execute it exactly within its ownership boundaries
```

Example:

```bash
git pull origin main && read /Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/docs/ecosystem/delegation/windsurf/NOTELETT_PHASE1_VERIFICATION.md and execute it exactly within its ownership boundaries
```

---

## Rules

- task files must stay bounded
- task files must name owned files or modules
- task files must name do-not-touch boundaries
- task files must include verification expectations
- Codex reviews delegated outputs before ecosystem completion is claimed
- each participant folder may also contain `FEEDBACK.md` for durable review notes and process corrections