Windsurf rules

1---
2name: execute-plan
3model: haiku
4description: "Batch-execute tasks from the active epic capsule sequentially, with a human checkpoint after each step. Use when user has an approved plan and wants step-by-step oversight."
5---
6 
7# Execute Plan
8 
9Execute tasks from the **active epic** (`specs/epics/eNN-slug/epic.yaml` story `tasks[]`) one at a time, showing evidence after each step before proceeding.
10 
11> **HARD GATE** — Do NOT proceed if on `main` or `master`. Run `kickoff-branch` first.
12>
13> **HARD GATE** — Active epic must exist with runnable `verify` on each task. If missing, run `plan-release` then `plan-work` or `build-epic`.
14 
15## Process
16 
17### 1. Read the plan
18 
19Read `specs/state.yaml` (`active_epic`, `active_story`) and the matching `specs/epics/*/epic.yaml`. Parse `depends-on` in task descriptions for execution waves.
20 
21> **CONTEXT ISOLATION** — Spawn each skill with a **fresh context window**. Pass decisions only through `specs/state.yaml` `handoff` — never rely on prior chat history.
22 
23Confirm with the user: step count, skip/reorder, stop-after step.
24 
25### 2. Execute step by step
26 
27For each task in the active story:
28 
29**a. Announce** — task `desc` and `verify` command.
30 
31**b. Execute** — code or `delegate-task` / `dispatch-agents` for waves.
32 
33**c. Run verify** — must be green before advancing.
34 
35**d. Log** — non-obvious decisions in `specs/state.yaml` under `decisions[]` or `handoff` block.
36 
37**e. Checkpoint** — ask to proceed unless autonomous mode requested.
38 
39**f. Story UAT** — after last task, run manual verification script from story notes or `verify-work`.
40 
41On verify failure: fix and re-run; never advance on red.
42 
43Update `specs/execution-status.yaml` when a story/epic completes (`bash scripts/sync-status-from-epics.sh` or direct edit).
44 
45### 3. Blockers
46 
47Report blocker; ask skip/adapt/stop; update epic capsule if plan changes.
48 
49### 4. Final report
50 
51Suggest: `verify-work` → `run-evals` → `audit-code` → `simulate-agents` → `commit-message` → `release-branch`
52 
53## Rules
54 
55- **Loop until behavioral correctness is verified**: if a verify command passes but the observed behavior is still wrong, return to step 1 and run the execution cycle again.
56 
57 
58 
59<!-- story: e02s03 -->
60<!-- story: e05s02 -->
61<!-- story: e08s01 -->
62