Claude Code mod
probe3
Permission override, subagent visibility, agent.spawn model rewrite, turn.step routing, prompt context injection
Install
git clone https://github.com/ucsandman/Agnostic-AI.git
claude --plugin-dir ./Agnostic-AI/labs/claude-mods/lab/probe3The repo has no marketplace file, so load the plugin folder directly with --plugin-dir.
What it can access
- Reach
- L2Writes or runs: writes files, reads files, reads settings, reads the transcript
- Sees
- every tool call, subagent spawns, every prompt
- Hooks
tool.checktool.callturn.stepagent.spawnsession.startagent.offerprompt.submitturn.complete
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
- ucsandman/Agnostic-AI
- Folder
labs/claude-mods/lab/probe3- License
- MIT
- Last updated
- 2 October 2026
- Listed in
- awesome-claude-code-mods
FAQ
What is probe3?
Permission override, subagent visibility, agent.spawn model rewrite, turn.step routing, prompt context injection It is a mod for Claude Code, from ucsandman/Agnostic-AI on GitHub.
What can the probe3 mod access?
Its widest reach is "writes or runs" (writes files, reads files, reads settings, reads the transcript). It sees every tool call, subagent spawns, every prompt. Like any mod, it runs with your permissions.
How do I install probe3?
Clone ucsandman/Agnostic-AI and start Claude Code with --plugin-dir pointing at the mod's folder (labs/claude-mods/lab/probe3).
Is probe3 popular?
ucsandman/Agnostic-AI has 24 GitHub stars and 0 forks, and is included in 1 curated Claude Code list. It was last updated on 2 October 2026.
More guard & safety mods
secret-pane
6bengous/claude-code-plugins
Claude asks for a secret in a masked box and gets a placeholder: the value stays in the session's memory, becomes real only inside a Bash command, is hidden again in every Bash and Read result and in the prompt, and never reaches the transcript; the mod writes nothing to disk
guardrails
8arasovic/claude-code-mods
Blocks shell commands you pick in /config: Cloudflare cf writes, attribution lines in commits and PRs, claude/ branch names. All rules start off
unity-tools
1kevinmedeiros/claude-mods
Unity no Claude Code: erros de compilação no contexto, painel de testes, build do servidor e guardas de arquivos
reread-guard
12VedantAndhale/claude-pro-kit
Stops Claude re-reading a file it already read in this conversation, with Read or a plain cat, sed -n, head, tail or Get-Content, when the file has not changed since; a deliberate second attempt still goes through.
safety-net
1TroyJLorents-GH/mod-squad
Blocks destructive tool calls before they run (force pushes, rm -rf outside the project, DROP TABLE, terraform destroy, writes to .env and keys, ...) and explains why.
bench
2mako-code/gobworks
Measures a command: warmup and timed runs, median/p95/stddev and outliers, two commands compared or a saved baseline per project, and a pane with a block distribution plot. Bounded, one at a time, never during Claude's turn unless Claude asked.
Browse the most popular Claude Code mods, all guard & safety mods, or the skills and MCP server directories.