Menu
Generate a risk-ordered implementation plan for a set of targets. Assesses blast radius per target, finds data flows between them, and produces a safe change sequence.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
Route to the right Ix skill or command for your task
Analyze system design — structure, coupling, code smells, and high-risk hotspots. Purely graph-based, no code reads.
Root cause analysis — trace execution path to a failure, narrow candidates, read minimal source only at suspected failure points.
Generate narrative-first, importance-weighted documentation for a repo, system, or subsystem with a selective reference layer. Use --full for deeper module/class/method coverage.
Change risk analysis — blast radius, affected systems, and what to test. Depth scales with risk level; low-risk targets stop early.
Deep dive into a symbol, feature, or bug. Graph-first, minimal code reads, early stopping when sufficient evidence found.
| name | ix-plan |
| description | Generate a risk-ordered implementation plan for a set of targets. Assesses blast radius per target, finds data flows between them, and produces a safe change sequence. |
Answer: in what order should these changes be made, what will break, and what needs testing?
If the Ix runtime is unavailable, ix_status will report this; fall back to manual assessment.
For most cases:
ix_query({ mode: "plan", targets: [$ARGUMENTS] })
Use the returned preview_markdown as the primary plan. Supplement below for high-risk targets.
If $ARGUMENTS contains symbol names, proceed directly.
If $ARGUMENTS is a description, first call in parallel:
ix_text({ pattern: $ARGUMENTS, limit: 10 })ix_locate({ symbol: $ARGUMENTS })Identify the 1-4 most relevant symbols.
For each target, call simultaneously:
ix_impact({ target: <target> })ix_callers({ symbol: <target> })Rank targets by risk level: critical > high > medium > low.
Call: ix_trace({ symbol: <highest-risk-target>, to: <second-target> })
Call: ix_depends({ symbol: <highest-risk-target>, depth: 2 })
# Change Plan
## Targets & Risk
| Target | Risk | Dependents | Key Callers |
|--------|------|------------|-------------|
| <A> | high | 12 | X, Y, Z |
| <B> | low | 2 | P |
## Change Order
Edit in this sequence to minimize breakage:
1. [target] — [reason]
2. ...
## Data Flow
[A -> trace path -> B — or "targets are independent"]
## Shared Risk
[Symbols affected by changes to multiple targets]
## Test Checkpoints
After [target A]: verify [specific callers]
After [target B]: verify [specific callers]
## Red Flags
- [any critical/high target needing extra care]
- [any cross-subsystem boundary being crossed]
Do not read source code unless a target cannot be resolved by ix_locate.