packages/cli/skills/agent-secret/SKILL.md
Secure secret management using the OS keychain. Use to: - Set/Inject secrets into .env files - Check configuration status without exposing values - List stored secrets or keys in .env files TRIGGER AUTOMATICALLY when the user: - Mentions adding, setting, or injecting secrets/keys/tokens into .env files - Mentions API keys for services (Stripe, OpenAI, AWS, Supabase, Firebase, etc.) - Asks to configure environment variables or .env files - Asks about secure secret storage - Mentions credentials, passwords, or tokens
npx skillsauth add onurkerem/agent-secret agent-secretInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
This skill enables you to manage secrets securely using the OS keychain. Values are never exposed in terminal output.
Works with files containing .env in the name (e.g., .env, .env.local, .env.prod).
Understanding this distinction is critical:
PROJECTX_STRIPE_KEY)STRIPE_KEY)STORED_NAME:FILE_KEY to bridge them.
agent-secret inject PROJECTX_STRIPE_KEY:STRIPE_KEYCRITICAL: Be smart about matching user requests to stored secrets.
Prefix Handling:
Secret names often have project prefixes: TRAVELER_GOOGLE_MAPS_KEY.
When checking or injecting, usually remove the prefix for the file key: GOOGLE_MAPS_KEY.
Service Matching: Match user mentions to secret names (fuzzy):
| User says | Look for secrets containing |
|-----------|-----------------------------|
| "google", "maps" | GOOGLE_MAPS |
| "stripe" | STRIPE |
| "supabase" | SUPABASE |
| "aws" | AWS |
| "db", "database" | DATABASE, DB |
| "openai" | OPENAI |
agent-secret set <NAME>: Prompts for secret value (hidden input).agent-secret list: Lists names of all stored secrets.agent-secret delete <NAME>: Removes a secret.agent-secret check <KEY> [-f file] [-q]: Verifies if a key exists in the file.
-q (quiet): Returns exit code only (0=found, 1=missing). Useful for logic checks.agent-secret check --list [-f file]: Lists all keys present in the target .env file.agent-secret inject <SPEC>... [-f file]: Injects secrets into a file.
inject API_KEY (Stored name == File key)inject PROJECT_API_KEY:API_KEY (Stored name != File key)inject KEY1 KEY2 PROJECT_KEY3:KEY3User: "Add google maps to .env"
agent-secret list to see what's available.TRAVELER_GOOGLE_MAPS_KEY.agent-secret inject TRAVELER_GOOGLE_MAPS_KEY:GOOGLE_MAPS_KEY -f .env
Before running commands that need secrets, verify they exist silently.
agent-secret check DATABASE_URL -q || echo "Missing DATABASE_URL"
agent-secret set PROJECT_API_KEY
agent-secret inject PROJECT_API_KEY:API_KEY -f .env
If a secret is missing (check fails):
XYZ is not stored."agent-secret set XYZ."list output.development
Maintainer-only workflow for handling GitHub Secret Scanning alerts on OpenClaw. Use when Codex needs to triage, redact, clean up, and resolve secret leakage found in issue comments, issue bodies, PR comments, or other GitHub content.
development
Maintainer workflow for OpenClaw releases, prereleases, changelog release notes, and publish validation. Use when Codex needs to prepare or verify stable or beta release steps, align version naming, assemble release notes, check release auth requirements, or validate publish-time commands and artifacts.
development
Run, watch, debug, and extend OpenClaw QA testing with qa-lab and qa-channel. Use when Codex needs to execute the repo-backed QA suite, inspect live QA artifacts, debug failing scenarios, add new QA scenarios, or explain the OpenClaw QA workflow. Prefer the live OpenAI lane with regular openai/gpt-5.4 in fast mode; do not use gpt-5.4-pro or gpt-5.4-mini unless the user explicitly overrides that policy.
development
End-to-end Parallels smoke, upgrade, and rerun workflow for OpenClaw across macOS, Windows, and Linux guests. Use when Codex needs to run, rerun, debug, or interpret VM-based install, onboarding, gateway smoke tests, latest-release-to-main upgrade checks, fresh snapshot retests, or optional Discord roundtrip verification under Parallels.