Skill Comply

skill-comply: Automated Compliance Measurement

Measures whether coding agents actually follow skills, rules, or agent definitions by:

1. Auto-generating expected behavioral sequences (specs) from any .md file
2. Auto-generating scenarios with decreasing prompt strictness (supportive → neutral → competing)
3. Running claude -p and capturing tool call traces via stream-json
4. Classifying tool calls against spec steps using LLM (not regex)
5. Checking temporal ordering deterministically
6. Generating self-contained reports with spec, prompts, and timelines

Supported Targets

• Skills (skills/*/SKILL.md): Workflow skills like search-first, TDD guides
• Rules (rules/common/*.md): Mandatory rules like testing.md, security.md, git-workflow.md
• Agent definitions (agents/*.md): Whether an agent gets invoked when expected (internal workflow verification not yet supported)

When to Activate

• User runs /skill-comply
• User asks "is this rule actually being followed?"
• After adding new rules/skills, to verify agent compliance
• Periodically as part of quality maintenance

Usage

# Full run
uv run python -m scripts.run ~/.claude/rules/common/testing.md

# Dry run (no cost, spec + scenarios only)
uv run python -m scripts.run --dry-run ~/.claude/skills/search-first/SKILL.md

# Custom models
uv run python -m scripts.run --gen-model haiku --model sonnet --classifier-model sonnet 

Models

| Stage | Default | Why | |-------|---------|-----| | --gen-model | haiku | Spec / scenario generation. Short prompts, fast. | | --model | sonnet | Scenario execution (the agent under test). | | --classifier-model | sonnet | Trace classification. Haiku times out on long traces (50+ events) and abstract specs (e.g. contemplative-axioms). Sonnet handles the load with a 300s timeout. |

Key Concept: Prompt Independence

Measures whether a skill/rule is followed even when the prompt doesn't explicitly support it.

Report Contents

Reports are self-contained and include:

1. Expected behavioral sequence (auto-generated spec)
2. Scenario prompts (what was asked at each strictness level)
3. Compliance scores per scenario
4. Tool call timelines with LLM classification labels

Advanced (optional)

For users familiar with hooks, reports also include hook promotion recommendations for steps with low compliance. This is informational — the main value is the compliance visibility itself.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: shimo4228
• Source: shimo4228/claude-harness
• License: MIT

Install and usage instructions live in the source repository linked above.