What is mcpx AGENTS.md?

Repository instructions for the mcpx project, covering its scope, working style, architecture boundaries, and checks for code changes. They also define the command structure for listing servers and calling their tools.

Use them when changing mcpx code, especially its command-line interface, server and tool dispatch, daemon lifecycle, caching, or performance-sensitive paths.

They give contributors a shared set of rules for making small, reviewable changes while preserving the project’s command behaviour. They also specify tests and build checks that help catch regressions.

How lydakis/mcpx configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to lydakis/mcpx. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/lydakis/mcpx/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/lydakis/mcpx

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/lydakis/mcpx/agents-md/github.svg)](https://agentmods.dev/instructions/lydakis/mcpx/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/lydakis/mcpx/agents-md"><img src="https://agentmods.dev/badge/instructions/lydakis/mcpx/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/lydakis/mcpx/agents-md"><img src="https://agentmods.dev/badge/instructions/lydakis/mcpx/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 540 This file is loaded in full into every session.

When invoked 540 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00540	$0.00540
Opus 5.5	$0.00216	$0.00216
Sonnet 5.5	$0.00108	$0.00108
Haiku 4.5	$0.00054	$0.00054

Measured 2mo ago against content hash d46ccb9d40f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcpx 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 2mo 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 · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Owner: George Lydakis (@lydakis)

Scope

This file applies to this repository.
Keep implementation aligned with docs/design.md.

Working Style

Keep diffs small and reviewable.
Favor root-cause fixes over patches.
For behavior changes and bug fixes, add/adjust tests first when practical.
Preserve the command contract unless intentionally changed:
- mcpx lists servers
- mcpx <server> lists tools
- mcpx <server> <tool> calls tool
If repeated review rounds on the same subsystem keep surfacing new P1s, stop patching locally and write a short reset plan before continuing.

Quality Gates

Run go test ./... for changed scope.
Run go vet ./....
Run go build ./....
For performance-sensitive changes (daemon lifecycle, CLI dispatch, cache/pool hot paths), run make perf; use make perf-loop when validating warm CLI throughput.
Benchmark checks are manual/non-blocking unless explicitly requested as a hard gate; when run, include commands and a short before/after summary in handoff.
If any gate cannot run, document why in handoff.

Architecture Boundaries

internal/cli: CLI argument parsing and UX surface only.
internal/daemon + internal/ipc: lifecycle, socket auth, dispatch.
internal/mcppool: MCP transport/session concerns only.
internal/response: MCP result unwrapping/mapping only.
internal/cache: cache keying and TTL storage only.

Runtime And Cache Invariants

Preserve strict same-CWD correctness without adding synchronous config I/O to the unchanged warm path.
Runtime source monitoring and fingerprinting must observe the same files, including config, fallback, auth, OAuth credentials, and symlink targets.
Requested tool names control cache policy. Resolved backend tool identities control cache storage and validation.
Check cold-daemon and keepalive-expired behavior when strengthening cache or tool-validation invariants.
Cover unchanged and changed same-CWD requests, invalid config, cold-daemon cache hits, stale tools, and symlinked source edits with regressions.

Read the full file on GitHub · 52 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.

2mo ago First seen · 52 lines · 540 tokens per session scan A d46ccb9d40f9

Subscribe to this mod's changes

mcpx AGENTS.md is an instructions file published in the GitHub repository lydakis/mcpx (55 stars, last pushed 23d ago), licensed MIT. It adds 540 tokens to every session, about $0.0022 per session on Opus 5.5. 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.

agent-workflows cli developer-tools mcp model-context-protocol shell

mcpx AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcpx AGENTS.mdlydakis/mcpx	Instructions file	55	23d ago	MIT	A	540	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

mcpx: Instructions file for Codex