claudecodemods.dev

All mods / ucsandman/agnostic-ai

harness-mods

CAUTION

★ 22 by Wes Sander Repository ↗ Mod source ↗

Safety & guards

Description

A guard layer for the agnostic-ai harness: heartbeat checks, subagent accounting, secret redaction, per-guard modes. Writes files and reads env vars to enforce policy.

What it can do

Reach level 2 — writes or runs What does this mean? →

writes filesreads filesreads env varspersists statedrawsother: $.runtime.supports

Can see: subagent spawns · every tool call · every prompt

Raw API calls (14) +
  • $.command.register
  • $.env.get
  • $.fs.exists
  • $.fs.read
  • $.fs.stat
  • $.fs.write
  • $.runtime.supports
  • $.session.id
  • $.session.model
  • $.session.usage
  • $.store.get
  • $.store.set
  • $.ui.log
  • $.ui.toast

Static check passed on Claude Code 2.1.302.

Install

$/plugin marketplace add ucsandman/agnostic-ai
$/plugin install harness-mods

Check the repo for the exact name.

Details

Repository
ucsandman/agnostic-ai
Path in repo
engine/mods/harness-mods
License
MIT
Last updated
Oct 2, 2026
First seen
Oct 4, 2026
Last scanned
Oct 19, 2026

Related mods — reach level 2

Capability data is machine-generated by static analysis and may be incomplete. A SAFE badge is not a guarantee — read the code before installing anything with broad access. Not affiliated with Anthropic.

Found a mistake in this listing or verdict? Report an issue →