A plugin containing instructions for how the Mewbo agent harness behaves, including limits, timeouts, file paths, deferred tools, and delegation.

Understanding result caps, timeout behavior, path handling, deferred tool calls, and delegation in the harness.

It helps agents account for the environment's operating rules while carrying out tasks.

harness — Plugin by bearlike

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code

/plugin marketplace add bearlike/Assistant

agentmods

npx agentmods add plugins/bearlike/assistant/harness

Clone the repo

git clone --depth 1 https://github.com/bearlike/Assistant

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

harness scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

packages/mewbo_core/src/mewbo_core/builtin_plugins/harness/.claude-plugin/plugin.json · 8 lines

What it actually says

{
  "name": "harness",
  "display_name": "Agent Harness",
  "description": "mewbo-harness skill — how this harness itself behaves (result caps, timeouts, paths, deferred tools, delegation).",
  "version": "0.1.0",
  "author": "Mewbo"
}

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

yesterday First seen · 8 lines scan A 6ad9f8c4a6e1

Subscribe to this mod's changes

harness is a plugin published in the GitHub repository bearlike/Assistant (41 stars, last pushed 7d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Data and AI LLM agents anthropic litellm openai self-hosted

overclick

Claim, execute, and deliver cards on your own self-hosted OverClick board. Ships the workflow skill, the /overclick: commands, and hooks: a session-start board snapshot and a delivery commit check run by default, while the claim guard and the stop/harness guards ship disabled. The only network endpoint is the OverClic.

ustoppble/overclick · not measured

harness

Getting it into your agent

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other plugins, from other repositories

overclick

claude-dynamic-workflows-codex

codex-workflows

claude-homelab

overclick

claude-homelab