Claude Code mod
watchdog
Watchdog agents review each update of the agent you work with and push short notes to it. It spawns review subagents and auto-allows only its own review spawn and reviewer reads of files the main agent already read.
Install
git clone https://github.com/matteoantoci/claude-code-watchdog.git
claude --plugin-dir ./claude-code-watchdog/plugins/watchdogThe repo has no marketplace file, so load the plugin folder directly with --plugin-dir.
What it can access
- Reach
- Unknown
- Sees
- /"."/u calls, every prompt, compaction
- Draws in
AbovePrompt- Hooks
state.setstore.settool.callturn.startturn.completeprompt.submitcommand.runsession.startui.renderui.presssession.endturn.stepsession.compactsession.append
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
- matteoantoci/claude-code-watchdog
- Folder
plugins/watchdog- Author
- Matteo Antoci
- License
- Apache-2.0
- Last updated
- 1 November 2026
- Listed in
- awesome-claude-code-mods
FAQ
What is watchdog?
Watchdog agents review each update of the agent you work with and push short notes to it. It spawns review subagents and auto-allows only its own review spawn and reviewer reads of files the main agent already read. It is a mod for Claude Code, from matteoantoci/claude-code-watchdog on GitHub.
What can the watchdog mod access?
Its reach could not be worked out from its code. It sees /"."/u calls, every prompt, compaction. It draws in AbovePrompt. Like any mod, it runs with your permissions.
How do I install watchdog?
Clone matteoantoci/claude-code-watchdog and start Claude Code with --plugin-dir pointing at the mod's folder (plugins/watchdog).
Is watchdog popular?
matteoantoci/claude-code-watchdog has 2 GitHub stars and 0 forks, and is included in 1 curated Claude Code list. It was last updated on 1 November 2026.
More memory & instructions mods
session-handoff-button
2gclbck-crealore/session-handoff-button-mod
A Session Hand-off button above the prompt, colored by context usage; reads Context clean and cannot be pressed while green. From orange on, one press writes the handoff, saves it to a temp .md, clears the session and continues in the fresh one with a short message while the handoff goes in as hidden context. Past 65% it stops your next prompt once and recommends the button.
exit-memory-update
manueldelgado/manueldelgado-mods
Before /exit, offers to update CLAUDE.md with the session's learnings (via claude-md-management when installed).
recall
2joeldg/claude-mods
Makes past sessions recallable: indexes Claude Code and Codex transcripts, subagent runs, memory files, standing orders and second-opinion reviews into a local SQLite index (kept after Claude Code deletes old transcripts), gives Claude search, expand, recap and list tools, and adds /recall (search, last session, timeline, decisions, commands, files, PRs, ask), /remember, a pick-up-where-you-left-off band, a related-work band, and a per-session ledger (goal, open tasks, questions answered, files touched, PRs and commits) that comes back after a compaction and /recall ledger prints. Nothing calls a model except /recall ask: one call to the ask model per question, billed to your usage.
anon-mode
1eveiljuice/claude-anon
claude anon — incognito mode: clean context (memory, CLAUDE.md, history unloaded), session not saved, transcript deleted at exit
MacLoad
2Heuwzen/claude-runway
Shows your Mac's CPU and memory under the prompt, names the app behind a slowdown, and warns when the Mac is overloaded
auto-handoff
1Akash001uts/claude-mods
Hands a long session off cleanly: at a context threshold Claude updates the docs and writes a handoff, the session compacts with its instructions, then a kickoff prompt carries on. Gives Claude a live context reading and a /wrap-up skill
Browse the most popular Claude Code mods, all memory & instructions mods, or the skills and MCP server directories.