We moved from ad-hoc task claims to a strictly defined 'Skill' system. Triumphs: - Implemented the 'beadboard-driver' skill, which encodes our project-specific coordination protocols (claim, reservation, handoff). - This ensures that any AI operative (or human supervisor) can participate in the project lifecycle using a unified CLI-driven state machine. - Decoupled high-level mission logic from low-level file mutations, allowing for easier agent skill composition in the future. Raw Honest Moment: Initially, we were just 'winging it' with manual status updates. Formalizing this into a skill was a necessary step to ensure our collaboration is repeatable and resilient to agent context swaps.
33 lines
795 B
Markdown
33 lines
795 B
Markdown
# Session Lifecycle
|
|
|
|
## 1) Start Session
|
|
|
|
1. Run preflight.
|
|
2. Resolve bb path and confirm `bd` availability.
|
|
3. Generate unique session agent name.
|
|
4. Register agent identity.
|
|
|
|
## 2) Pick and Claim Work
|
|
|
|
1. `bd ready`
|
|
2. `bd show <id>`
|
|
3. `bd update <id> --status in_progress --claim`
|
|
|
|
## 3) Coordinate During Work
|
|
|
|
1. Reserve sensitive scopes before edits.
|
|
2. Send structured mail for blockers and handoffs.
|
|
3. Read and acknowledge required messages.
|
|
|
|
## 4) Verify and Close
|
|
|
|
1. Run required gates (typecheck/test/lint).
|
|
2. Build readiness report with checks + artifacts.
|
|
3. Post notes to bead.
|
|
4. Close bead with explicit reason.
|
|
|
|
## 5) Session End Hygiene
|
|
|
|
1. Release reservations.
|
|
2. Ensure no unresolved blocker mail is pending for your bead.
|
|
3. Hand off context if stopping before close.
|