Stats
Actions
Tags
From ac-safety
Interactively configure ac-safety plugin's safety.yaml: customize guardians for credentials, destructive bash, file writes, supply chain risks, and Playwright via prompts and overrides.
How this skill is triggered — by the user, by Claude, or both
Slash command
/ac-safety:configure-safetyThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Interactive safety.yaml configuration for ac-safety plugin.
Interactive safety.yaml configuration for ac-safety plugin.
/configure-safety or /ac-safety:configure-safety
Read the 3-tier config resolution and display current effective config:
${CLAUDE_PLUGIN_ROOT}/config/safety.default.yaml~/.claude/safety.yaml./safety.yaml (relative to project root)Display current effective settings per guardian:
Ask user which guardian(s) to customize.
For each selected guardian, present current category decisions and ask for changes:
category: current_decisiondeny, ask, or allow per categoryAsk target location: project-level (./safety.yaml) or user-level (~/.claude/safety.yaml).
Generate or update the YAML file at chosen location.
Validate by loading the merged config and displaying effective result.
1. Read ${CLAUDE_PLUGIN_ROOT}/config/safety.default.yaml
2. Read ~/.claude/safety.yaml (if exists)
3. Read ./safety.yaml (if exists)
4. Display merged effective config as table
5. Prompt: "Which guardian to customize? (credential/destructive_bash/write_scope/supply_chain/playwright/all)"
6. For selected guardian(s):
a. Show categories with current decisions
b. Ask for new decision per category (or skip)
c. For list fields, show current and ask for changes
7. Prompt: "Save to project-level or user-level? (project/user)"
8. Write YAML with only the overrides
9. Re-read and display new effective config
safety.default.yaml)npx claudepluginhub waterplanai/agentic-config --plugin ac-safetyConfigures CC Safety Net blocking rules at user, project, or shareable GitHub scope. Reads existing configs, suggests rules from project context, writes valid JSON, and validates with sync, verify, and test commands.
Configures Claude Code security settings with permission wildcards, shell operator protections, and project-level access controls. Use for securing tools like Bash and workflows.
Enforces tiered runtime guardrails on Claude Code agent actions: auto-approves reads/routines, notifies on writes/commits, requires approval for installs/emails/deletes, blocks credential leaks/sudo. Logs audits.