risk-classification

Original：🇺🇸 English

Translated

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.

2installs

Sourceathola/claude-night-market

Added on2026-03-02

NPX Install

npx skill4agent add athola/claude-night-market risk-classification

SKILL.md Content

View Translation Comparison →

Risk Classification

Overview

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.

When To Use

Assessing risk of tasks before agent assignment
Determining verification requirements for task completion
Deciding parallel execution safety between tasks
Adding risk markers to task checklists

When NOT To Use

Single-file trivial changes (assume GREEN)
Strategic architecture decisions (use full
```
Skill(attune:war-room)
```
instead)
Non-code tasks (documentation-only, configuration comments)

4-Tier Risk Model

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

Hybrid Routing

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.

Task Metadata Extension

Add risk tier to task metadata for downstream consumption:

json

{
  "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).

Module Reference

tier-definitions.md: Detailed tier criteria, boundaries, and override mechanism
heuristic-classifier.md: File-pattern rules for automated classification
verification-gates.md: Per-tier verification requirements and parallel safety matrix

Integration Pattern

yaml

# In your skill's frontmatter
dependencies: [leyline:risk-classification]

For Task Generators

Append

[R:TIER]

marker to task format:

markdown

- [ ] T012 [P] [US1] [R:YELLOW] Create LoginForm component in src/components/LoginForm.tsx

For Orchestrators

Check risk tier before task assignment:

if task.risk_tier in ["RED", "CRITICAL"]:
    invoke Skill(attune:war-room-checkpoint) for RS scoring
    if CRITICAL: require human approval before proceeding

Exit Criteria

Every task has a risk tier assigned (explicit or default GREEN)
RED/CRITICAL tasks have war-room-checkpoint RS scores
Verification gates passed for the assigned tier
No parallel execution of prohibited tier combinations