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/xhuw/async-bash-mcp/agents-mdgit clone --depth 1 https://github.com/xhuw/async-bash-mcpWrote 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/xhuw/async-bash-mcp/agents-md)<a href="https://agentmods.dev/instructions/xhuw/async-bash-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/xhuw/async-bash-mcp/agents-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 | $0.00311 | $0.00311 |
| Opus 5 | $0.00156 | $0.00156 |
| Sonnet 5 | $0.00062 | $0.00062 |
| Haiku 4.5 | $0.00031 | $0.00031 |
Grade A, and why
async-bash-mcp AGENTS.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 3d 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.
What it actually says
AGENTS.md
Build / lint / test
- Install dev deps: uv sync --extra dev
- Run full tests: uv run pytest
- Run a single test: uv run pytest tests/test_async_bash_mcp.py::test_spawn
- Lint (ruff): uv run ruff check
Code style & conventions
- Use Python 3.13+ features conservatively; maintain clear, simple code.
- Formatting: follow ruff/PEP 8. Use black-style line lengths ~88. Keep imports grouped: stdlib, third-party, local.
- Imports: always use absolute imports from package root (e.g. from async_bash_mcp import spawn).
- Types: annotate public functions and methods with type hints. Prefer built-in typing (list/dict) per py3.13.
- Naming: snake_case for functions and variables, PascalCase for classes, UPPER_SNAKE for constants.
- Errors: raise specific exceptions. Validate inputs early and return plain serializable types for MCP responses.
- Logging: prefer logging module, avoid print in library code. Keep messages concise and testable.
Agents operating here
- Follow repo scripts in pyproject.toml for entrypoints.
- No Copilot or Cursor rules found; if added later, include .github/copilot-instructions.md and .cursor/rules/* in this file.
- Store all notes about progress being make and plans in the
notes/directory
Keep this file short and machine-readable; update when style tools change.
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.
- 3d ago First seen · 27 lines · 311 tokens per session scan A 04f1f2055d5f
async-bash-mcp AGENTS.md is an instructions file published in the GitHub repository xhuw/async-bash-mcp (6 stars, last pushed 1y ago), licensed MIT. It adds 311 tokens to every session, about $0.0016 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 2026-08-31.
Other instructions, from other repositories
daz-mcp-server CLAUDE.md
Instructions for bluemoonfoundry/daz-mcp-server, covering claude.md (project index), primary commands, skill modules (reference with @), architecture summary and render api (dazscriptserver native endpoints).
mcpscore AGENTS.md
Instructions for mcp-box/mcpscore, covering agent instructions for mcpscore and gotchas (learned the hard way).
vector_mcp AGENTS.md
AGENTS.md instructions for sergiobayona/vector_mcp, covering agents.md, project overview, essential commands, development setup and testing and quality.
mcp-scribe CLAUDE.md
Instructions for The-Swarm-Corporation/mcp-scribe, covering claude.md, what this is, commands, formatting: black only. do not run ruff format and architecture.
bitrise-mcp CLAUDE.md
Instructions for bitrise-io/bitrise-mcp, covering bitrise mcp server and tool definitions.
mcp-router CLAUDE.md
Claude Code instructions for mcp-router/mcp-router, a project described as: A Unified MCP Server Management App (MCP Manager).