A sandboxed command-line toolkit for Claude Code, with Unix commands, code editing and analysis, Python and JavaScript execution, search, and task/worktree management.

Useful for searching repositories, making focused edits, reviewing diffs, running scripts, and coordinating coding tasks across worktrees.

It gives the coding agent one place to inspect, change, and run project files while restricting execution in a sandbox.

ag-bash — Plugin by sairam0424

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 sairam0424/ag-bash

agentmods

npx agentmods add plugins/sairam0424/ag-bash/ag-bash

Clone the repo

git clone --depth 1 https://github.com/sairam0424/ag-bash

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

ag-bash 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 2d ago.

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.

plugins/ag-bash/.claude-plugin/plugin.json · 27 lines

What it actually says

{
  "$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
  "name": "ag-bash",
  "displayName": "Ag-Bash",
  "version": "6.0.4",
  "description": "Sandboxed AI-native bash for Claude Code: 70 MCP tools backed by the @ag-bash/bash engine — run_bash with a full unix toolkit (grep/sed/awk/jq), surgical code edit/diff/analyze, WASM Python & JavaScript, semantic search, and agent task/worktree management. Defense-in-depth sandbox on by default.",
  "author": {
    "name": "Ag-Bash",
    "email": "[email protected]"
  },
  "homepage": "https://github.com/sairam0424/ag-bash#readme",
  "repository": "https://github.com/sairam0424/ag-bash",
  "license": "Apache-2.0",
  "keywords": [
    "bash",
    "shell",
    "mcp",
    "model-context-protocol",
    "sandbox",
    "agentic",
    "ai-agents",
    "code-execution",
    "wasm",
    "typescript"
  ]
}

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.

2d ago First seen · 27 lines scan A defec56c04ad

Subscribe to this mod's changes

ag-bash is a plugin published in the GitHub repository sairam0424/ag-bash (0 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 2026-08-30.

Git and workflow Planning Research agentic-workflows ai-agents bash-shell mcp-server observability sandboxing

ag-bash

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

personal-corp-os

dotskills

trigger-tree

notify

flagrare

datapowers-dev