agent-ops-kit
A Claude Code plugin that enforces three guardrails for AI agents shipping code: requiring command output to back operational claims, scanning builds against a regex deny list to strip personal data and credentials before sharing, and building private and public variants from one source to prevent drift. The kit includes three skills (evidence-gate, scrub-before-share, two-variant-release), two commands (/scrub-check and /release-public), and a review subagent (release-auditor) that validates build safety before publication.
Install
What it's made of
2 commands · 1 agent · 3 skills
- Commands
- 2
- Agents
- 1
- Skills
- 3
- MCP servers
- 0
- Hooks
- 0
What it needs & plugs into
- API keys
- none
- Paid services
- none detected
- External tools
- none
- Talks to
- nothing external detected
Analyzed . Facts extracted from the plugin's files. Prose generated by claude-haiku-4-5-20251001.
Is this your plugin?
Claim it to keep the card accurate and enter the weekly contest. Requires signing in as the GitHub owner (thefiredev-cloud).