Tool Policy — Testing skill for Claude Code
Write your company's rules for an agent's tool calls, test them on past traces, and run them on every change.
How to install Tool Policy
Installs to ~/.claude/skills/ryanalberts-pmstack-tool-policy/SKILL.md
mkdir -p ~/.claude/skills/ryanalberts-pmstack-tool-policy && curl -fsSL https://raw.githubusercontent.com/RyanAlberts/pmstack/HEAD/commands/tool-policy.md -o ~/.claude/skills/ryanalberts-pmstack-tool-policy/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Tool Policy does
description: Write your company's rules for an agent's tool calls, test them on past traces, and run them on every change argument-hint: "[trace file or project.json]"
Use the Skill tool to run the `pmstack-tool-policy` skill from the pmstack plugin with these arguments: $ARGUMENTS. If the skill is not available, tell the user to run /plugin install pmstack@pmstack.
Alternatives in Testing
- Pua — Use when the user invokes /pua or asks for PUA mode, try-harder/retry help, change-approach coaching, completi 19.5k ★
- Claude Codepro — by Max Ritter - Professional development environment for Claude Code with spec-driven workflow, TDD enforcemen 1.6k ★
- Test TDD — Run when user calls /test-tdd 957 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Skill Context Diet
Claude Code may truncate CLAUDE.md past 40,000 chars. Compact rules first; test bounded context ablation with
Rtk Test Before Merge
Force the agent to write or extend a test for every behaviour change.
Spec-Flow Agents
Spec-Flow coordinates multiple coding tools through a single shared canon. Every agent must read the same rule
E2e
Generate and run end-to-end tests with Playwright. Creates test journeys, runs tests, captures screenshots/vid
Make Traces
Make realistic test traces when you have no real ones yet
Baron
Local-first AI coding agent orchestrator with a terminal UI — isolated worktrees, a real build/lint/test gate,
Related Agents
Regression Prevention
Regression Prevention Agent (SSDF RV.3.3–RV.3.4). Write-capable for tests, lint/static-analysis rules, and har
Workspace Governance
Read-only governance specialist for AGENTS layering, repo rules, release law, and change-scope policy. Invoke
Sms Assistant Test Writer
Use this agent when the user needs to write or improve unit tests for the SMS assistant functionality, particu