Claude Code mod

harness-mods

Harness Mod layer: heartbeat/canary, native usage, rewrite explanations, measured subagent accounting, supervisor routing, secret redaction. Modes per guard in ~/.claude/mods/mods-config.json (classic | shadow_mod | mod).

24 starsGuard & safety modsValidates on Claude Code 2.1.316 Source

Install

From source

git clone https://github.com/ucsandman/Agnostic-AI.git
claude --plugin-dir ./Agnostic-AI/engine/mods/harness-mods

The 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 env vars, persists state, draws, other: $.runtime.supports
Sees: subagent spawns, every tool call, every prompt
Hooks: session.startruntime.emitagent.spawntool.callprompt.submitturn.completecommand.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.

Claude Code docs

Details

Repository: ucsandman/Agnostic-AI
Folder: engine/mods/harness-mods
Author: Wes Sander
Type: Guard & safety mods
License: MIT
Last updated: 2 October 2026
Listed in: awesome-claude-code-mods

FAQ

What is harness-mods?

What can the harness-mods mod access?

Its widest reach is "writes or runs" (writes files, reads files, reads env vars, persists state, draws, other: $.runtime.supports). It sees subagent spawns, every tool call, every prompt. Like any mod, it runs with your permissions.

How do I install harness-mods?

Clone ucsandman/Agnostic-AI and start Claude Code with --plugin-dir pointing at the mod's folder (engine/mods/harness-mods).

Is harness-mods 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

cs-mermaid

hex/claude-sessions

Draws mermaid flowcharts in replies inline, as coloured blocks and lines.

Guard & safety mods

screen-guard

danyuchn/claude-mods

Masks sensitive names, orgs and secrets in the transcript for screen sharing; /mask toggles, click a mask to reveal

Guard & safety mods/plugin install

lemo-guard

lemomo-ai/lemo-mod

限时：Claude 单轮工作超时自动中止 · 等你确认的时间不计 · 默认关闭，在「安全」页开启 / Time limit: stops Claude when a turn runs over time · time waiting for you does not count · off by default, switch on in Safety

Guard & safety mods/plugin install

secret-redactor

escapeboy/claude-code-kit

Hides tokens, keys and passwords in tool output as ‹secret:N›, restores them in later tool calls, blocks reading key files.

Guard & safety mods/plugin install

turn-receipt

yoshihiko555/dotfiles

Keeps a per-turn tally of edits, runs, curls and destructive commands and shows it on the turn footer; any non-read-only Bash counts as a run, a claim (English or Japanese) with no run flags the spinner, a destructive Bash unfolds its tool group, and an edit-without-run turn suggests running the tests.

Guard & safety mods/plugin install

scope-guard

1.1k

YeonwooSung/my-claude-code-mods

Scope Guard

Guard & safety mods/plugin install

Browse the most popular Claude Code mods, all guard & safety mods, or the skills and MCP server directories.