cordum
The action firewall for AI agents. Enforce policy and human approval before risky tool calls, shell commands, workflows, and production changes, with auditable evidence.
- 511 stars
- 34 forks
- 18 open issues
- Language: Go
- License: NOASSERTION
- updated
Install
git clone https://github.com/cordum-io/cordum && cp cordum/*.md ~/.claude/agents/- Clone the repository and copy the agent .md definitions into ~/.claude/agents (or .claude/agents inside a project).
- Start a new Claude Code session to load the agents.
- Delegate work to them with the Task/Agent tool or by name.
Subagents overview
What people ask about cordum
What is cordum-io/cordum?
cordum-io/cordum is subagents for the Claude AI ecosystem. The action firewall for AI agents. Enforce policy and human approval before risky tool calls, shell commands, workflows, and production changes, with auditable evidence. It has 511 GitHub stars and its last recorded update is dated 2026-10-21.
How do I install cordum?
You can install cordum by cloning the repository (https://github.com/cordum-io/cordum) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is cordum-io/cordum safe to use?
Our security agent has analyzed cordum-io/cordum and assigned a Trust Score of 82/100 (tier: Trusted). See the full breakdown of passed checks and flags on this page.
Who maintains cordum-io/cordum?
cordum-io/cordum is maintained by cordum-io. The last recorded GitHub activity is dated 2026-10-21, with 18 open issues.
Are there alternatives to cordum?
Yes. On ClaudeWave you can browse similar subagents at /categories/agents, sorted by popularity or recent activity.