ix-impact

Run `command -v ix` to verify ix is on PATH. Never use tilde paths (`~/...`) or absolute paths — always invoke `ix` directly via PATH. If not found, use Grep to find all usages and estimate impact manually. ## Goal Answer: *what breaks if this changes, and is it safe to proceed?* Stop as early as the risk level allows. ## Phase 1 — Risk score (always) ```bash timeout 60s ix impact $ARGUMENTS --format llm ``` **Immediately classify:** | Risk level | Action | |---|---| | `low` + < 3 dependents | **STOP** — safe to proceed. Report and suggest verification targets. | | `medium` OR 3–10 dependents | Go to Phase 2 | | `high` or `critical` OR > 10 dependents | Go to Phase 2 + 3 | ## Phase 2 — Callers and dependents (medium/high/critical) Run in parallel: ```bash timeout 60s ix callers $ARGUMENTS --limit 20 --format llm timeout 60s ix depends $ARGUMENTS --depth 2 --format llm ``` Extract: direct callers by name and subsystem, transitive count. **Stop here if risk is `medium`:** report callers, suggest verification, done. ## Phase 3 — Import chain and subsystem spread (high/critical only) ```bash timeout 60s ix imported-by $ARGUMENTS --format llm ``` Cross-reference callers + dependents + importers to identify: - Which subsystems are in the blast radius - Whether the change crosses an architectural boundary - Any tests that cover the affected paths ## Output ``` ## Impact: [target] **Risk level:** <critical | high | medium | low> **Verdict:** <SAFE TO PROCEED | REVIEW CALLERS FIRST | NEEDS CHANGE PLAN> **Blast radius:** - Direct dependents: N - Transitive (depth 2): M - Subsystems affected: [list — only if phase 3 ran] **Key callers:** [top 5, with subsystem label] **At-risk behaviors:** [from ix impact atRiskBehavior field] **Recommended action:** - low: proceed, verify [specific callers] - medium: test [caller list] after change - high/critical: run `/ix-plan $ARGUMENTS` before editing ``` Never read source code in this skill. Risk analysis is purely graph-based.