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.
npx agentmods add instructions/sairam0424/ag-bash/claude-mdgit clone --depth 1 https://github.com/sairam0424/ag-bashWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/sairam0424/ag-bash/claude-md)<a href="https://agentmods.dev/instructions/sairam0424/ag-bash/claude-md"><img src="https://agentmods.dev/badge/instructions/sairam0424/ag-bash/claude-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01213 | $0.01213 |
| Opus 5 | $0.00607 | $0.00607 |
| Sonnet 5 | $0.00243 | $0.00243 |
| Haiku 4.5 | $0.00121 | $0.00121 |
Grade A, and why
ag-bash CLAUDE.md 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
Ag-Bash is an AI-native bash interpreter written in TypeScript. It is organized as a pnpm monorepo:
@ag-bash/bash: The core shell engine, filesystem, and sandboxed runtimes.@ag-bash/agent-bridge: Terminal UI bridge for AI agent communication.@ag-bash/mcp-server: Standalone Model Context Protocol server.- Version Baseline:
6.0.4(fixed-mode synchronized across all packages)
Distribution
Ag-Bash ships across multiple channels, all at the current 6.0.4 baseline (owner sairam0424, Apache-2.0):
# npm (library + servers, synchronized at 6.0.4)
npm i @ag-bash/bash # core engine library
npx @ag-bash/mcp-server # standalone MCP server (70 tools, stdio)
# MCP server in Claude Code
claude mcp add ag-bash -- npx -y @ag-bash/mcp-server
# Claude Code plugin
/plugin marketplace add sairam0424/ag-bash
/plugin install ag-bash@ag-bash
# Homebrew (installs ag-bash, ag-shell, ag-bash-mcp bins)
brew tap sairam0424/tap && brew install ag-bash
- MCP Registry:
io.github.sairam0424/ag-bash@6.0.4(active, isLatest) at registry.modelcontextprotocol.io. - Docker MCP Catalog: submission PR open at
docker/mcp-registry(in review; not yet merged).
Commands
Global Workspace Commands
# Build & Setup
bash scripts/force-build.sh # Full monorepo force build (Core + MCP)
pnpm install # Install dependencies
pnpm typecheck # Type check all packages
# Verification
bash scripts/e2e-verify.sh # Run full E2E verification suite
Core Engine Commands (packages/bash)
# Testing
pnpm --filter @ag-bash/bash test:run # Run ALL engine tests
pnpm --filter @ag-bash/bash test:unit # Fast unit tests
pnpm --filter @ag-bash/bash test:wasm # WASM runtimes (python, sqlite)
# Interactive Development
pnpm --filter @ag-bash/bash shell # Run the interactive ag-shell
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.
- 6d ago First seen · 106 lines · 1,213 tokens per session scan A e0307949760e
ag-bash CLAUDE.md is an instructions file published in the GitHub repository sairam0424/ag-bash (0 stars, last pushed 3d ago), licensed Apache-2.0. It adds 1,213 tokens to every session, about $0.0061 per session on Opus 5. 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.
Other instructions, from other repositories
signoz-mcp-server CLAUDE.md
Claude Code instructions for SigNoz/signoz-mcp-server, covering claude.md — development conventions, feature planning convention, rules, git & pr and code style.
remnote-mcp-server AGENTS.md
AGENTS.md instructions for robert7/remnote-mcp-server, covering agents.md, repo role, companion repos (sibling dirs), contract map (current) and external mcp tool surface (17).
lain copilot-instructions.md
Copilot instructions for spuentesp/lain, covering lain — codebase intelligence, when to use lain, the most useful tools, workflows and caveats.
mcp-read-only-grafana CLAUDE.md
Instructions for lukleh/mcp-read-only-grafana, covering claude.md, project overview, runtime config location, development commands and install dependencies.
sentry-mcp AGENTS.md
AGENTS.md instructions for VitalyOstanin/sentry-mcp, covering repository guidelines, contributor notes, planning workflow, documentation guidelines and language policy.
mcp-read-only-grafana AGENTS.md
Instructions for lukleh/mcp-read-only-grafana, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.