What is xmcp AGENTS.md?

A repository instruction file for coding agents working on the xmcp project. It explains which area-specific guidance to read, how the project is organized, and the standards for changes and reviews.

Use it to guide work in the xmcp repository, including framework, command-line, plugin, example, and website changes. It also covers formatting, linting, logging, and review checks.

It gives agents the project rules they need before editing code, such as supported tools, documentation expectations, and dependency limits.

xmcp AGENTS.md — Instructions file by basementstudio

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.

agentmods

npx agentmods add instructions/basementstudio/xmcp/agents-md

Clone the repo

git clone --depth 1 https://github.com/basementstudio/xmcp

Made for: Codex, OpenCode.

Per session 487 This file is loaded in full into every session.

When invoked 487 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00487	$0.00487
Opus 5	$0.00244	$0.00244
Sonnet 5	$0.00097	$0.00097
Haiku 4.5	$0.00049	$0.00049

Measured 2d ago against content hash 6831a23e6044, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

xmcp 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 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.

AGENTS.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent guidance - xmcp

This file is the root instruction set for coding agents and contributors. Read the scoped AGENTS.md file for any area you touch:

packages/AGENTS.md for framework, CLI, scaffolder, and plugin packages.
examples/AGENTS.md for examples.
apps/website/AGENTS.md for the docs site and website.

Repo basics

Use Node 22 and pnpm.
All changes target main. There is no canary branch; canary npm releases are cut from main as Changesets snapshot releases.
Keep PRs focused. If related work appears while editing, leave it for a follow-up unless it is required for the current fix.
User-facing feature or behavior changes need docs and a runnable example. If an example is not appropriate, explain why in the PR.
Prefer existing patterns and helper APIs over new abstractions.
Do not add dependencies unless the repo already has no reasonable primitive for the job.

Review standards

Apply these before handing work back:

Use repo formatting and linting, not editor defaults.
Keep logs minimal. Do not add process narration or debug logs.
Do not add fixed setTimeout or setInterval numbers unless the delay is a named constant with a clear reason. Prefer signal-based flow.
Avoid broad rewrites, especially in compiler, loader, runtime, and scaffold paths.
Preserve transport semantics. Do not turn stateless HTTP flows into stateful session-based flows, or stateful flows into stateless ones, unless the task explicitly requires that transport contract change.
Stateless HTTP must not depend on server-side memory from previous requests. Any client metadata needed by tools after initialize must be repeated in the current request, not recovered from a hidden session/cache.
Do not force users to wrap every tool, resource, or prompt for a framework feature.
Keep config fields optional when values can be inferred safely.
Delete stale examples instead of patching deprecated patterns.
Explain non-obvious choices in code or PR notes: new hooks, wrappers, required fields, timers, plugin registration, and foundational rewrites.

Read the full file on GitHub · 47 lines

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 · 47 lines · 487 tokens per session scan A 6831a23e6044

Subscribe to this mod's changes

xmcp AGENTS.md is an instructions file published in the GitHub repository basementstudio/xmcp (1,324 stars, last pushed 3d ago), licensed MIT. It adds 487 tokens to every session, about $0.0024 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.

framework mcp modelcontextprotocol

xmcp AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Agent guidance - xmcp

Repo basics

Review standards

What this file has done since we first saw it

Other instructions, from other repositories

ida-pro-mcp CLAUDE.md

jesse AGENTS.md

laravel AGENTS.md

tableau-mcp CLAUDE.md

AgentEval copilot-instructions.md

LarAgent AGENTS.md