Skip to content

hashgraph-online/awesome-codex-plugins / plugins/alelaguard/agentguards-plugins/skills/setup

Set up and verify AgentGuards in Codex. Use when the user asks to configure AgentGuards, set their API key, or check that the guardrails are wired up correctly.

FileKindSize
SKILL.mdskill md2.2 KB
---
name: setup
description: Set up and verify AgentGuards in Codex. Use when the user asks to configure AgentGuards, set their API key, or check that the guardrails are wired up correctly.
---

# AgentGuards setup

Guide the user through finishing AgentGuards setup after installing the plugin.
The plugin already bundles the enforcing hooks — the only thing the user must
supply is their API key.

## Steps

1. **Check for the API key.** The hooks use the first of: the
   `AGENTGUARDS_API_KEY` environment variable, `~/.codex/agentguards_token`,
   then `~/.agentguards/credentials.json`. If none holds a key starting with
   `ag_`, the easiest fix is the AgentGuards CLI: `agentguards login` signs in
   through the browser and saves the key where the hooks read it (install the
   CLI from https://agentguards.co if it isn't there). Otherwise, tell the user
   to:
   - Get a key from the dashboard at https://agentguards.co/dashboard/keys
   - Export it so the hooks can read it. For the current shell and future
     sessions, add to their shell profile (`~/.bashrc`, `~/.zshrc`, etc.):

     ```
     export AGENTGUARDS_API_KEY=ag_your_token_here
     ```

   - Restart Codex (or start a new session) so the hooks pick up the key.

2. **Confirm the URL (optional).** AgentGuards defaults to
   `https://prod.agentguards.co`. Only set `AGENTGUARDS_URL` if the user runs a
   self-hosted instance.

3. **Fail-open vs fail-closed.** The hooks fail **closed** by default — if the
   AgentGuards service is unreachable, actions are blocked. A user who prefers
   availability over strict enforcement can set `AGENTGUARDS_FAIL_OPEN=true`.
   Mention this only if they ask or report unexpected blocks.

4. **Verify.** Run the checks in the `status` skill yourself: they prove the key
   is **accepted** (HTTP 200), not just present. If it fails, the most common
   cause is `AGENTGUARDS_API_KEY` not being exported in the environment Codex
   was launched from.

5. **Summarize what is now active:** prompt screening, shell-command
   authorization (with Codex's approval prompt for anything borderline),
   scanning of content fetched by shell commands, and security scanning of
   `apply_patch` edits.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall