Inline risk classification for agent tasks using a 4-tier model. Hybrid routing: GREEN/YELLOW use heuristic file-pattern matching, RED/CRITICAL escalate to war-room-checkpoint for full reversibility scoring.
Provides inline risk classification for agent tasks using a 4-tier model (GREEN/YELLOW/RED/CRITICAL). Uses fast heuristic file-pattern matching for low-risk tiers and delegates to Skill(attune:war-room-checkpoint) for high-risk tiers requiring full reversibility scoring.
Skill(attune:war-room) instead)| Tier | Color | Scope | Example | Verification |
|---|---|---|---|---|
| GREEN | Safe | Single file, trivial revert | Test files, docs, utils | None required |
| YELLOW | Caution | Module-level, user-visible | Components, routes, views | Conflict check + test pass |
| RED | Danger | Cross-module, security/data | Migrations, auth, database schema | War-room RS + full test + review |
| CRITICAL | Stop | Irreversible, regulated | Data deletion, production deploy | War-room RS + human approval |
Task received
|
v
Heuristic classifier (file patterns)
|
├── GREEN/YELLOW → Apply tier, continue
|
└── RED/CRITICAL → Invoke Skill(attune:war-room-checkpoint)
for reversibility scoring (RS)
|
└── RS confirms or adjusts tier
Why hybrid: GREEN/YELLOW classification is fast and deterministic (file pattern matching). RED/CRITICAL tasks warrant the overhead of full reversibility analysis because the cost of getting them wrong is high.
Add risk tier to task metadata for downstream consumption:
{
"id": "5",
"subject": "Add user authentication",
"metadata": {
"risk_tier": "YELLOW",
"risk_reason": "Modifies src/components/LoginForm.tsx (user-visible component)",
"classified_at": "2026-02-07T22:00:00Z"
}
}
Tasks without risk_tier metadata default to GREEN (backward compatible).
# In your skill's frontmatter