Claude Code mod
harness
Skills and guard hooks: ai-code-cleanup, interrogate, shape-task, verify-change, setup, a shared-worktree git guard, and a guard against reading API-key config files
Install
/plugin marketplace add Paradox07127/claude-utopia
/plugin install harness@claude-utopiaMods install like plugins. Run /reload-plugins or start a new session to load it.
What it can access
- Reach
- L2Writes or runs: runs processes, writes files, drives Claude, reads files, reads env vars, reads settings, reads the transcript, reads mod state, persists state, draws
- Sees
- classic hooks, subagent spawns, every prompt
- Hooks
classic.PreToolUseagent.spawnprompt.mentionagent.offertool.describesession.startturn.stepturn.completeprompt.submitsession.endclassic.SessionStartclassic.PostModelSwitchclassic.Stopcommand.run
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
- Paradox07127/claude-utopia
- Folder
plugins/harness- Marketplace
claude-utopia- Author
- Paradox07127
- License
- MIT
- Last updated
- 18 October 2026
- Listed in
- awesome-claude-code-mods
FAQ
What is harness?
Skills and guard hooks: ai-code-cleanup, interrogate, shape-task, verify-change, setup, a shared-worktree git guard, and a guard against reading API-key config files It is a mod for Claude Code, from Paradox07127/claude-utopia on GitHub.
What can the harness mod access?
Its widest reach is "writes or runs" (runs processes, writes files, drives Claude, reads files, reads env vars, reads settings, reads the transcript, reads mod state, persists state, draws). It sees classic hooks, subagent spawns, every prompt. Like any mod, it runs with your permissions.
How do I install harness?
Inside Claude Code (v2.1.287 or later), run /plugin marketplace add Paradox07127/claude-utopia and then /plugin install harness@claude-utopia.
More guard & safety mods
guardrails
azoof-ahmed/claude-mods
A lint gate for Claude's edits: your project's rules, a baseline of existing violations, and a PreToolUse check that refuses only edits adding new ones.
mission-control
aecheman27-gif/claude-mods
Mission-control skin: [SYS]/[TOOL]/[EDIT] tool rows with per-tool icons and one status block above the prompt (under flightdeck's session log while its pane is open): [SYS] repo, branch, model, hw-guard; [CTL] model and effort buttons; [CTX] context fill with a /ctx pane by tool. /clean for a checklist view.
entregas
plasdigital/mods-claude-code-kit-aluno
Guarda todo arquivo que a IA cria ou edita, em qualquer conversa: /entregas lista com link, e um "cadê" já chega respondido
mod-firewall
bbarney7/claude-code-mods
A firewall for Claude Code mods: watches what every other mod does (network, processes, secret files, env vars) and asks, blocks or logs
dev-guard
sonata39-star/claude-mod
Blocks catastrophic commands, asks before risky ones, and stops secrets from being written into files
redact
JinhaoFang/claude-mods
Rewrites sensitive data (emails, IPs, credentials, addresses) out of what enters the model context
Browse the most popular Claude Code mods, all guard & safety mods, or the skills and MCP server directories.