risk-classification
/risk-classification
Klasyfikuje zadania agenta do czterech poziomów ryzyka (GREEN, YELLOW, RED, CRITICAL), by ocenić odwracalność działania przed wyborem sposobu postępowania.
- Autor
- athola ↗
- Repozytorium
- claude-night-market ↗
- Licencja
- MIT
- Ostatnia zmiana repozytorium
- 01.10.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 6
- Skrypty
- 0
- Komentarze HTML
- 0
- Adresy URL w SKILL.md
- 0
Brak sygnałów. Repozytorium zmienione 01.10.2026, bez odwołań do wycofanych modeli i API.
MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.
Co robi i kiedy
Klasyfikuje zadania agenta do czterech poziomów ryzyka (GREEN, YELLOW, RED, CRITICAL), by ocenić odwracalność działania przed wyborem sposobu postępowania.
Oryginalny opis (EN)
Classifies agent tasks into 4 risk tiers (GREEN/YELLOW/RED/CRITICAL). Use when assessing action reversibility before committing to an approach.
Jak działa
- Overview
- When To Use
- When NOT To Use
- 4-Tier Risk Model
- Hybrid Routing
- Task Metadata Extension
- Readiness Levels
- Graduated Autonomy
- Module Reference
- Integration Pattern
Podgląd SKILL.md
---
name: risk-classification
description: Classifies agent tasks into 4 risk tiers (GREEN/YELLOW/RED/CRITICAL). Use when assessing action reversibility before committing to an approach.
alwaysApply: false
category: infrastructure
tags:
- risk
- classification
- safety
- verification
- gates
dependencies:
- error-patterns
provides:
infrastructure:
- risk-tier-classification
- verification-gates
- heuristic-classifier
patterns:
- risk-aware-coordination
- tier-based-verification
usage_patterns:
- task-risk-assessment
- verification-gate-routing
- parallel-safety-validation
complexity: intermediate
model_hint: standard
estimated_tokens: 500
progressive_loading: true
modules:
- modules/tier-definitions.md
- modules/heuristic-classifier.md
- modules/verification-gates.md
- modules/readiness-levels.md
- modules/automation-tiers.md
role: library
---
# 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 and test pass |
| **RED** | Danger | Cross-module, security/data | Migrations, auth, database schema | War-room RS, full test, and review |
| **CRITICAL** | Stop | Irreversible, regulated | Data deletion, production deploy | War-room RS and 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).
## Readiness Levels
The 4-tier Readiness Levels system provides clear risk
classification with required controls per tier:
| Level | Name | When | Required Controls |
|-------|------|------|-------------------|
| 0 | Routine | Low blast radius, easy rollback | Basic validation, rollback step |
| 1 | Watch | User-visible changes | Review, negative test, rollback note |
| 2 | Elevated | Security/compliance/data | Adversarial review, risk checklist |
| 3 | Critical | Irreversible, regulated | Human confirmation, two-step verification |
See `modules/readiness-levels.md` for full level definitions,
selection decision tree, and integration guidance.
## Graduated Autonomy
Risk classification sets how carefully a change is verified.
Automation tiers set how autonomously the agent acts and when it
must hand control back. Each risk tier carries a default automation
tier (GREEN to A3 autonomous, CRITICAL to A0 manual), and a
pre-licensed downgrade trigger drops the agent one tier on repeated
failure, confidence loss, a stakes spike, or repo-state mismatch
rather than re-prompting at the same level. See
`modules/automation-tiers.md` for the tier table and the downgrade
trigger, and `imbue:assisted-mastery` for the explain/produce mode
selection that reads from it.
## 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
- **readiness-levels.md**: 4-tier risk system with required controls per level
- **automation-tiers.md**: Per-tier autonomy defaults and the downgrade trigger
## 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
- Each task carries an automation tier; downgrades are recorded
with a reason when a trigger fires
Pliki w paczce (6)
- SKILL.md 6 KB
- modules/automation-tiers.md 3 KB
- modules/heuristic-classifier.md 4 KB
- modules/readiness-levels.md 8 KB
- modules/tier-definitions.md 3 KB
- modules/verification-gates.md 4 KB
Wersje
| Repozytorium | Wynik | Licencja |
|---|---|---|
| Ta strona · athola/claude-night-market | 100 | MIT |
| SimonFoote-greensparx/CopilotForge | 100 | CC-BY-4.0 |
Migawka bazy z 13.11.2026 · wersja paczki b9e183d5aa9a (skrót SHA-256 całej paczki)
Pobrania w ostatnich 30 dniach: 0 · ranking
Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.
Podobne skille
- 100token-budget-gate
Szacuje koszt tokenów przed wieloetapowym zadaniem i wydaje werdykt w czterech kolorach, a potem porównuje z faktem. - 85symptom_scorer
Przypisuje strukturalny wynik nasilenia (0-100) i kolor triage (RED, YELLOW, GREEN) zgłoszonym objawom podczas wstępnej diagnozy, a wynik steruje komunikatem o pilności. - 100nda-triage
Szybko selekcjonuje NDA z klasyfikacją GREEN, YELLOW lub RED, wg 10-punktowej listy kontrolnej dla przychodzących umów, do kierowania na akceptację. - 100task-classification
Klasyfikuje zadania, ustala złożoność i wybiera agenta, a także określa wymagania weryfikacji przy zmianach wielokomponentowych. - 100quick-recap
Dodaje do odpowiedzi agenta konwencję końcowego bloku statusu w kolorach czerwony, żółty i zielony, m.in. przez instalację zarządzanych instrukcji AGENTS.md lub CLAUDE.md. - 100pa-workflow-transactional-nda-triage-red-yellow-green
Szybko ocenia NDA w kolorach czerwonym, żółtym lub zielonym i rekomenduje podpisanie, poprawki albo eskalację.