Agent skill

agent-enforcement

Multi-agent orchestration enforcement for /team command. Provides claudish CLI validation, validates session directory paths, and ensures /team internal Tasks use dev:researcher. Use when debugging /team orchestration failures.

View SKILL.md on GitHub Repository
Stars 248
Forks 27

Install this agent skill to your Project

npx add-skill https://github.com/MadAppGang/claude-code/tree/main/plugins/multimodel/skills/agent-enforcement

SKILL.md

Agent Enforcement Skill

Overview

Two-layer defense against orchestration violations in /team:

  1. PreToolUse hook (hooks/enforce-team-rules.sh) — runtime violation blocker
  2. Model upgrade (team.md: model: opus) — better instruction following

How /team Invokes Models

Model Type Method Tool Reliability
Internal (Claude) Task(dev:researcher) Task tool High (same process)
External (Grok, Gemini, etc.) Bash(claudish --model) Bash tool 100% (deterministic CLI)

External models are called via claudish CLI directly from Bash — no LLM delegation needed.

Hook Rules (enforce-team-rules.sh)

The PreToolUse hook intercepts Task and Bash tool calls at runtime:

Rule Condition Action
1 /team Task with wrong agent DENY (must be dev:researcher)
2 /tmp/ in Task prompt DENY

Layer 1: PreToolUse Hook

Detects /team workflows by vote template pattern in Task prompts. Blocks:

  • Wrong agent for /team Tasks: Only dev:researcher is allowed for internal model Tasks
  • Insecure paths: No /tmp/ paths in Task prompts (use ai-docs/sessions/)

Layer 2: model: opus

The /team command uses model: opus (Opus 4.6) which follows complex XML instructions much more reliably than Sonnet (~90% vs ~33% compliance).

Agent Selection for Task Delegation

Task Type Primary Agent Alternatives
Investigation dev:researcher dev:debugger
Review agentdev:reviewer frontend:reviewer
Architecture dev:architect frontend:architect, agentdev:architect
Implementation dev:developer frontend:developer, agentdev:developer
Testing dev:test-architect frontend:test-architect
DevOps dev:devops —
UI/Design dev:ui frontend:designer, frontend:ui-developer

Pre-processor (resolve-agents.sh)

The /team command can optionally call resolve-agents.sh to determine agent and method for each model before launching:

bash
bash "${CLAUDE_PLUGIN_ROOT}/scripts/resolve-agents.sh" \
  --models "internal,x-ai/grok-code-fast-1" \
  --task-type "investigation"

Output:

json
{
  "sessionDir": "ai-docs/sessions/team-slug-timestamp-random",
  "taskType": "investigation",
  "resolutions": [
    { "modelId": "internal", "method": "direct", "agent": "dev:researcher" },
    { "modelId": "x-ai/grok-code-fast-1", "method": "cli", "agent": "dev:researcher" }
  ]
}

Methods:

  • "direct" — Internal Claude via Task(agent)
  • "cli" — External model via Bash(claudish --model)

Validation

Run the test suite to verify enforcement:

bash
cd autotest/team && bash run-tests.sh

Troubleshooting

Hook blocking legitimate calls: The hook triggers on /team vote template patterns in Task prompts and claudish in Bash commands. Normal Task usage (without vote templates) is never affected.

resolve-agents.sh not found: The /team command uses its own built-in logic. The hook still provides runtime protection.

Hook behavior: The hook skips existence checks (which claudish, command -v claudish).

Recommended Agent Skills

Expand your agent's capabilities with these related and highly-rated skills.

MadAppGang/claude-code

test-skill

A test skill for validation testing. Use when testing skill parsing and validation logic.

248 27
Explore
MadAppGang/claude-code

bad-skill

248 27
Explore
MadAppGang/claude-code

claudish-usage

CRITICAL - Guide for using Claudish CLI ONLY through sub-agents to run Claude Code with OpenRouter models (Grok, GPT-5, Gemini, MiniMax). NEVER run Claudish directly in main context unless user explicitly requests it. Use when user mentions external AI models, Claudish, OpenRouter, or alternative models. Includes mandatory sub-agent delegation patterns, agent selection guide, file-based instructions, and strict rules to prevent context window pollution.

248 27
Explore
MadAppGang/claude-code

release

Plugin release process for MAG Claude Plugins marketplace. Covers version bumping, marketplace.json updates, git tagging, and common mistakes. Use when releasing new plugin versions or troubleshooting update issues.

248 27
Explore
MadAppGang/claude-code

claudish-integration

248 27
Explore
MadAppGang/claude-code

openrouter-trending-models

Fetch trending programming models from OpenRouter rankings. Use when selecting models for multi-model review, updating model recommendations, or researching current AI coding trends. Provides model IDs, context windows, pricing, and usage statistics from the most recent week.

248 27
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results