A Caushell integration that performs semantic analysis of shell actions before Harness runs them. Harness is a system for automating software delivery and related operations.

Use it when Harness jobs run shell commands and you want those actions checked by Caushell before execution.

It provides an extra interpretation step before automated shell commands execute, helping identify what an action means before it changes a system.

caushell — Plugin by fatmo666

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 fatmo666/Caushell

agentmods

npx agentmods add plugins/fatmo666/caushell/marketplace

Clone the repo

git clone --depth 1 https://github.com/fatmo666/Caushell

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

caushell 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.

.claude-plugin/marketplace.json · 21 lines

What it actually says

{
  "$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
  "name": "caushell",
  "description": "Caushell integrations for pre-execution semantic analysis of Harness shell actions.",
  "owner": {
    "name": "Caushell"
  },
  "plugins": [
    {
      "name": "caushell-claude",
      "description": "Session-aware shell guardrails for Claude Code backed by the Caushell runtime.",
      "author": {
        "name": "Caushell"
      },
      "category": "security",
      "source": "./integrations/claude-code",
      "homepage": "https://github.com/fatmo666/Caushell"
    }
  ]
}

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 · 21 lines scan A df800a4f87dc

Subscribe to this mod's changes

caushell is a plugin published in the GitHub repository fatmo666/Caushell (6 stars, last pushed yesterday), licensed Apache-2.0. 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 2026-08-31.

Guardrails Security bash claude-code claude-code-plugin codex shell-security

caushell

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

agmsg

probity

ngernthongdee

dcotelo

codoop-flow

agent-messaging