Matrix Code Review
Perform comprehensive, context-aware code review using 5-agent architecture with 95% false positive reduction.
Tip: This skill runs in a forked context for an unbiased perspective - similar to how a human reviewer would approach the code for the first time.
Architecture
ORCHESTRATOR (parses target, routes, aggregates)
│
├── DETECTION AGENT → security, runtime, breaking, logic flaws, hygiene (nuke)
├── IMPACT AGENT → blast radius, transitive graph, test coverage
├── TRIAGE AGENT → tier assignment, confidence calibration, noise filter
├── REMEDIATION AGENT → context-aware fixes, regression checks
└── VERIFICATION AGENT → build, test, lint validation
Usage
Parse user arguments from the skill invocation (text after the trigger phrase).
Expected format: <target> [mode]
- target: File path, PR number, or "staged" for staged changes
- mode (optional):
default | lazy (default: from config or default)
Modes
Default Mode (Comprehensive)
Full 5-agent review pipeline with maximum index utilization:
- Detection: Security vulns, runtime issues, breaking changes, hygiene (nuke scan)
- Impact: Transitive blast radius (2-3 levels), service boundaries, test coverage
- Triage: Tier classification, >80% signal ratio target
- Remediation: Context-aware fixes matching codebase patterns
- Verification: Run build, test, lint commands automatically
Lazy Mode (Quick)
Detection agent only:
- Direct code inspection
- Critical issues only (Tier 1)
- ~2-3 comments, no blast radius
Review Pipeline
Follow the 5-agent orchestration detailed in references/review-phases.md:
- Orchestrator - Parse target, dispatch agents, aggregate results
- Detection Agent - Find security, runtime, breaking, logic issues
- Impact Agent - Calculate transitive blast radius, test coverage
- Triage Agent - Classify tiers, calibrate confidence, filter noise
- Remediation Agent - Generate fixes, check regression risk
- Verification Agent - Run build, test, lint; report results
Early exit: If Detection finds nothing critical, skip Impact/Triage depth.
Examples
/matrix:review src/utils/auth.ts # Default mode (comprehensive)
/matrix:review staged # Review staged changes
/matrix:review staged lazy # Quick review of staged changes
/matrix:review 123 # Review PR #123
/matrix:review 123 lazy # Quick review of PR #123
Additional Resources
Reference Files
references/review-phases.md - Orchestrator + 5-agent pipeline
references/agents/detection.md - Detection patterns and output format
references/agents/impact.md - Blast radius algorithm
references/agents/triage.md - Tier classification and signal ratio
references/agents/remediation.md - Fix generation and regression checks
references/agents/verification.md - Build/test/lint command detection and execution
Converted and distributed by TomeVault — claim your Tome and manage your conversions.
1---2name: matrix-code-review3description: This skill should be used when the user asks to "review this code", "review PR", "code review", "review staged changes", "blast radius analysis", "check impact of changes", or needs comprehensive context-aware code review. Use when this capability is needed.4---56# Matrix Code Review78Perform comprehensive, context-aware code review using 5-agent architecture with 95% false positive reduction.910> **Tip:** This skill runs in a **forked context** for an unbiased perspective - similar to how a human reviewer would approach the code for the first time.1112## Architecture1314```15ORCHESTRATOR (parses target, routes, aggregates)16 │17 ├── DETECTION AGENT → security, runtime, breaking, logic flaws, hygiene (nuke)18 ├── IMPACT AGENT → blast radius, transitive graph, test coverage19 ├── TRIAGE AGENT → tier assignment, confidence calibration, noise filter20 ├── REMEDIATION AGENT → context-aware fixes, regression checks21 └── VERIFICATION AGENT → build, test, lint validation22```2324## Usage2526Parse user arguments from the skill invocation (text after the trigger phrase).2728**Expected format:** `<target> [mode]`2930- **target**: File path, PR number, or "staged" for staged changes31- **mode** (optional): `default` | `lazy` (default: from config or `default`)3233## Modes3435### Default Mode (Comprehensive)36Full 5-agent review pipeline with maximum index utilization:37- Detection: Security vulns, runtime issues, breaking changes, **hygiene (nuke scan)**38- Impact: Transitive blast radius (2-3 levels), service boundaries, test coverage39- Triage: Tier classification, >80% signal ratio target40- Remediation: Context-aware fixes matching codebase patterns41- Verification: Run build, test, lint commands automatically4243### Lazy Mode (Quick)44Detection agent only:45- Direct code inspection46- Critical issues only (Tier 1)47- ~2-3 comments, no blast radius4849## Review Pipeline5051Follow the 5-agent orchestration detailed in `references/review-phases.md`:52531. **Orchestrator** - Parse target, dispatch agents, aggregate results542. **Detection Agent** - Find security, runtime, breaking, logic issues553. **Impact Agent** - Calculate transitive blast radius, test coverage564. **Triage Agent** - Classify tiers, calibrate confidence, filter noise575. **Remediation Agent** - Generate fixes, check regression risk586. **Verification Agent** - Run build, test, lint; report results5960**Early exit:** If Detection finds nothing critical, skip Impact/Triage depth.6162## Examples6364```65/matrix:review src/utils/auth.ts # Default mode (comprehensive)66/matrix:review staged # Review staged changes67/matrix:review staged lazy # Quick review of staged changes68/matrix:review 123 # Review PR #12369/matrix:review 123 lazy # Quick review of PR #12370```7172## Additional Resources7374### Reference Files7576- **`references/review-phases.md`** - Orchestrator + 5-agent pipeline77- **`references/agents/detection.md`** - Detection patterns and output format78- **`references/agents/impact.md`** - Blast radius algorithm79- **`references/agents/triage.md`** - Tier classification and signal ratio80- **`references/agents/remediation.md`** - Fix generation and regression checks81- **`references/agents/verification.md`** - Build/test/lint command detection and execution8283---84> Converted and distributed by [TomeVault](https://tomevault.io/claim/ojowwalker77) — claim your Tome and manage your conversions.85<!-- tomevault:4.0:skill_md:2026-04-11 -->