Claude Code mod
agent-state
Shows the state of Claude (working, permission, input, idle, background, compacting) in the iTerm2 tab subtitle and in a Sessions pane in the desktop app.
Install
/plugin marketplace add M-i-k-e-l/agent-state
/plugin install agent-state@agent-stateMods install like plugins. Run /reload-plugins or start a new session to load it.
What it can access
- Reach
- L3Network: MCP servers, runs processes, writes files, reads files, reads env vars, draws
- Sees
- classic hooks, every tool call, compaction
- Draws in
SessionModePane- Hooks
session.startclassic.SessionStartclassic.UserPromptSubmitsession.attachui.closeui.rendersession.endturn.startturn.completeclassic.Stoptool.callsession.compactclassic.PermissionRequesttelemetry.log
From a static scan of the mod's code by awesome-claude-code-mods. It shows what the code asks for, not a security review.
How Claude Code mods work
- A mod is a plugin with a JavaScript or TypeScript module that runs inside Claude Code (version 2.1.287 or later). It can draw panes beside the transcript, a band above the prompt, buttons and toasts, restyle the spinner and tool rows, and watch or rewrite tool calls and prompts.
- It installs like any plugin: add its marketplace with /plugin marketplace add owner/repo, then /plugin install name@marketplace.
- Check what a mod can reach before installing: it runs with your permissions. Reach goes from drawing only, to reading files, to writing files or running processes, to the network. Run claude plugin validate on a clone to list its hooks and calls without running it.
- Turn one off from the Installed tab in /plugin, or start Claude Code with --safe-mode to skip every customization for a session.
Details
- Repository
- M-i-k-e-l/agent-state
- Folder
.- Marketplace
agent-state- Author
- M-i-k-e-l
- License
- MIT
- Last updated
- 30 October 2026
- Listed in
- awesome-claude-code-mods
FAQ
What is agent-state?
Shows the state of Claude (working, permission, input, idle, background, compacting) in the iTerm2 tab subtitle and in a Sessions pane in the desktop app. It is a mod for Claude Code, from M-i-k-e-l/agent-state on GitHub.
What can the agent-state mod access?
Its widest reach is "network" (MCP servers, runs processes, writes files, reads files, reads env vars, draws). It sees classic hooks, every tool call, compaction. It draws in SessionMode, Pane. Like any mod, it runs with your permissions.
How do I install agent-state?
Inside Claude Code (v2.1.287 or later), run /plugin marketplace add M-i-k-e-l/agent-state and then /plugin install agent-state@agent-state.
More guard & safety mods
agent-state
kleinheinczg/claude-code-agent-state-mod
Reports what a Claude Code session is really doing (idle / working / tool / permission, plus signals and token use) from inside the session, as a JSON snapshot and a JSONL event log
approve-blocked
adammhal/claude-mods
Retries an auto-mode-blocked call up to three times so Claude Code's own permission prompt (and Moshi) can ask you.
agent-guard
AbyssCN/claude-lead-harness
Guard for dispatching subagents: denies isolation "worktree", checks a declared WORKTREE is a separate, clean, never-dispatched git worktree, and in opted-in repos requires non-read-only subagents to declare one.
arcade
shabier/claude-plugins
Five games in the docked side pane: Rail Runner, Road Hopper, Block Drop, Flap, 2048. Hides below 110 columns.
agent-cross-check
naoanao/agent-cross-check
When another coding agent (or a person) commits to your repo, Claude notices, runs mechanical checks (line endings, secrets, .env files, and the agent's report against the real files: missing files, silent videos, unconfirmed claims) and audits the commits by diff and tests. A git push waits until they are reviewed.
archgate
aarontan-bot/Claude-mod
Architecture map + plan gate: the AI maps modules, declares a scope, you approve it, and edits outside that scope are blocked and observed.
Browse the most popular Claude Code mods, all guard & safety mods, or the skills and MCP server directories.