Agentd — Development skill for Claude Code
🛡️ Local daemon that guards & observes coding-agent hooks — one policy for Claude, Cursor, Codex & more.
How to install Agentd
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open macrox-pro/agentd and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Agentd does
🛡️ Local daemon that guards & observes coding-agent hooks — one policy for Claude, Cursor, Codex & more.
Alternatives in Development
- Coding Agent Session Search — Unified TUI and CLI to index and search your local coding agent session history across 11+ providers (Codex, C 708 ★
- AgentHandover — What if OpenClaw, Claude Code, Codex etc. knew how to do your work without you saying it 600 ★
- Lacp — Local-first policy, evidence, memory, and recovery controls for Claude, Codex, Hermes, and other CLI coding ag 300 ★
README
agentd
A local daemon that proxies, guards, and observes coding-agent hooks — once, for every agent.
agentd sits between your AI coding agents (Claude Code, Cursor, Codex, Gemini CLI, OpenCode, Kimi Code) and your hook logic. Agents invoke a thin CLI entrypoint; a user-level daemon applies policies, dispatches sync and async pipelines, and returns provider-correct responses. Built on [agenthooks](https://github.com/speakeasy-api/agenthooks) for wire compatibility.
[](https://pkg.go.dev/github.com/macrox-pro/agentd)  
**Status:** v0.0.3 (policy.offline). Roadmap history: [PROGRESS.md](./PROGRESS.md#milestones-archive).
Documentation
- User guide (English) — default (why agentd)
- Руководство (русский) (зачем нужен)
- Keeping docs current: docs/en/maintaining.md
Contributor design and conventions: [DESIGN.md](./DESIGN.md), [AGENTS.md](./AGENTS.md), [CONVENTIONS.md](./CONVENTIONS.md). How to contribute: [CONTRIBUTING.md](./CONTRIBUTING.md).
Research
Structured verbatim excerpts from primary sources — used when designing provider support, hooks, and conventions. Each tree has its own index and `SOURCES.md`.
| Tree | Focus |
|---|---|
| research/best-practice | Go best practices (Go ≥ 1.26.7) |
| research/claude-code | Claude Code docs — agent loop, hooks, MCP, settings, skills, plugins, cloud, enterprise |
| [resear |
Related Skills
Haptic Bridge
Local daemon that turns Claude Code / Codex lifecycle events (permission prompt, waiting for input, turn done)
Open Jev Approvals
Fail-closed binary (allow/deny) approval gate for Codex and Claude Code hooks — every intercepted tool call is
Agentjail
Policy guardrails for coding agents (Claude Code, Codex, Cursor) — every tool call is checked locally, before
Agenthooks
Author coding-agent hooks once in Go — Claude Code, Cursor, Codex, Gemini CLI, OpenCode, Kimi Code
Prompt Sensei
Local-first prompt coach for Claude Code and Codex that improves prompts, observes prompting habits, and analy
Plugin Better Tools
Better Tools is a Codex plugin that observes supported tool calls through a PreToolUse hook and turns that loc
Related Agents
Monk Installer
Install, upgrade, and troubleshoot monk-agent plus Monk CLI/daemon for Claude, Codex, and Cursor users.
Loom Daemon
Loom Daemon operator - Tier 2 daemon-mode surface that observes the running Rust loom-daemon binary via MCP to
Hcs Hook Integrator
Wires Claude Code + Codex hooks to the HCS substrate without embedding policy in hook bodies. Maintains .claud