enforcement

Installation
SKILL.md

Enforcement

Runtime mechanisms that block invalid actions.

Core Principle

"Rules are instructions, not enforcements. Systems need verification gates, not more documentation."

Instructions

  1. Identify what needs enforcement (not just documentation)
  2. Choose hook timing: PreToolUse, PermissionRequest, SubagentStop
  3. Implement blocking logic: scripts/block-*.sh
  4. 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)
Related skills

More from ingpoc/skills

Installs
7
Repository
ingpoc/skills
GitHub Stars
7
First Seen
Jan 25, 2026