Windsurf rules

1---
2name: assess-impact
3model: sonnet
4description: "Analyze the blast radius of a proposed change before any code is written. Maps dependents, affected stories, and test coverage. Produces specs/IMPACT_LATEST.md. Use before plan-work on any non-trivial change, when touching a shared module, or when the user asks \"what does this break?\"."
5---
6 
7# Assess Impact
8 
9> **HARD GATE** — Run this skill before `plan-work` whenever a change touches an existing module, symbol, or file used by more than one caller. Skip only for net-new code with no existing dependents.
10 
11Find the blast radius of the proposed change before a single line is written.
12 
13## Modes
14 
15- Default: full impact analysis (dependents + affected stories + test coverage mapping)
16- --lightweight: Fast fan-in/fan-out only (<10s). Maps callers and imports without test coverage mapping. Used by build-epic step 2 as a pre-plan gate. Risk score > 7 triggers a mandatory grill-me session before proceeding.
17 
18## Process
19 
20### 1. Identify the target
21 
22Name the symbol, module, or file being changed. If the user hasn't specified, ask one question: "What exactly are you changing?"
23 
24### 2. Find dependents
25 
26```
27grep -rn "[symbol-name]" . --include="*.ts" | grep -v node_modules
28git log --oneline -10 -- [file-path]
29```
30 
31→ verify: `test -f specs/IMPACT_LATEST.md || test -d specs/bugs`
32 
33### 3. Map to release plan stories
34 
35Read `specs/release-plan.yaml + epic capsule directories` (if it exists). For each dependent found in Step 2, identify which story owns that module. List stories that will be affected by the change.
36 
37→ verify: `test -f specs/release-plan.yaml && grep -ci "stor" specs/release-plan.yaml`
38 
39### 4. List test coverage
40 
41Find tests that exercise the target:
42 
43```
44grep -rn "[symbol-name]" . --include="*.test.*" --include="*.spec.*"
45```
46 
47→ verify: `test -d specs/epics || test -d skills`
48 
49### 5. Classify risk
50 
51| Level | Condition |
52|-------|-----------|
53| Low   | ≤ 2 callers, all covered by tests |
54| Medium | 3–10 callers, partial test coverage |
55| High  | > 10 callers, or shared API/interface, or no tests |
56 
57### 6. Write specs/IMPACT_LATEST.md
58 
59```
60## Target
61[symbol or file being changed]
62 
63## Dependents ([count])
64- [file]: [caller or usage]
65 
66## Affected Stories
67- Story [X.Y]: [title]
68 
69## Test Coverage
70- [test file]: covers [scenario]
71- Gap: [untested behavior]
72 
73## Risk: Low / Medium / High
74[One-sentence rationale]
75 
76## Recommended action
77[Proceed / Add tests first / Discuss design]
78```
79 
80→ verify: `grep "Risk:" specs/IMPACT_LATEST.md`
81 
82Suggest `plan-work` once risk is understood and any test gaps are noted.
83 
84## Risk score gating
85 
86In `--lightweight` mode (used by build-epic step 2), assign a numeric risk score (1–10):
87- Fan-in (how many callers): 0–4 points
88- Fan-out (how many dependencies the module itself uses): 0–3 points  
89- Recent churn (git log --oneline -5 count): 0–3 points
90 
91**Risk score > 7**: Gate — require a `grill-me` session before proceeding to implementation. Document the grill-me result in the impact report at `specs/IMPACT-<epic>-<story>.md`.
92