npx skills add https://github.com/ingpoc/skills --skill enforcementSKILL.md
Enforcement
Runtime mechanisms that block invalid actions.
Core Principle
"Rules are instructions, not enforcements. Systems need verification gates, not more documentation."
Instructions
- Identify what needs enforcement (not just documentation)
- Choose hook timing: PreToolUse, PermissionRequest, SubagentStop
- Implement blocking logic:
scripts/block-*.sh - Test with invalid action → verify block
Blocking Mechanisms
| Mechanism | How | Effect |
|---|---|---|
| Exit code 2 | exit 2 + stderr | Blocks, feeds stderr to Claude |
| JSON deny | "permissionDecision": "deny" | Structured blocking |
| Stop block | "decision": "block" | Forces agent to continue |
Hook Timing
| Event | Can Block? | Use Case |
|---|---|---|
| PreToolUse | Yes | Validate before execution |
| PermissionRequest | Yes | Custom approval logic |
| SubagentStop | Yes | Force quality gates |
| PostToolUse | No | Feedback only |
References
| File | Load When |
|---|---|
| references/blocking-hooks.md | Implementing hook mechanisms |
| references/quality-gates.md | Designing verification loops |
| references/hook-templates.md | Writing hook code |
| references/agent-harness-hooks.md | Agent-harness specific patterns |
| references/sandbox-runtime.md | OS-level MCP server isolation |
| references/sandbox-fast-path.md | Hybrid security (allowlist + sandbox for 2-3x speed) |
Repository
ingpoc/skillsParent repository
Repository Stats
Stars5
Forks0