What is mcp-nexus AGENTS.md?

Repository-specific instructions for AI agents and developers working on the fyrlabs/mcp-nexus TypeScript project. They describe the project, commands, file structure, and coding rules.

Use them when modifying mcp-nexus, especially when building, type-checking, testing, linting, benchmarking, or preparing a release.

They give contributors the rules needed to make changes that fit the repository and to run its required checks.

How fyrlabs/mcp-nexus configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to fyrlabs/mcp-nexus. 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/fyrlabs/mcp-nexus/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/fyrlabs/mcp-nexus

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/fyrlabs/mcp-nexus/agents-md/github.svg)](https://agentmods.dev/instructions/fyrlabs/mcp-nexus/agents-md)

Your own site

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

Per session 894 This file is loaded in full into every session.

When invoked 894 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	$0.00894	$0.00894
Opus 5.5	$0.00358	$0.00358
Sonnet 5.5	$0.00179	$0.00179
Haiku 4.5	$0.00089	$0.00089

Measured 2mo ago against content hash e6f53ddafc52, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-nexus 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 · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Rules and conventions for AI agents (and humans) working in this repository. Personal/global agent instructions live separately — see ~/.claude/CLAUDE.md (loaded via ~/.claude/instructions/*). If this file and a user's global instructions conflict, the stricter engineering rule wins inside this repo.

Project

Package: @fyrlabs/mcp-nexus — a local-first MCP router. The product contract is mcp-nexus-product-spec.md at the repo root; treat it as the architecture reference.
Runtime: TypeScript ESM on Node.js >= 22.13 (first Node line where node:sqlite is available unflagged; 24 LTS recommended). No native deps.
Do not add mandatory network dependencies, telemetry, or cloud calls.

Commands

npm run build       # tsc -p tsconfig.build.json -> dist/
npm run typecheck   # strict tsc over src/ including tests
npm run test        # vitest run (unit + integration)
npm run lint        # eslint src/
npm run bench       # build + synthetic benchmark (search latency, context reduction)

All four must pass before committing anything non-trivial (bench is optional locally, run it when touching search/ranking). npm pack --dry-run before any release commit.

Structure rules

Source lives in src/; tests live in src/tests/ and mirror the source tree (e.g. src/router/ranker.ts → src/tests/router/ranker.test.ts or a matching <area>/<area>.test.ts file). Shared test helpers go in src/tests/helpers/.
Public API is only what src/index.ts exports. Keep exports deliberate.
Keep subsystems behind their interfaces (transport factory, embedding provider, storage). No cross-module reach-ins past constructors.

Code style

Strict TypeScript: no any, no non-null assertions unless provably safe, import type for type-only imports, .js extensions on relative imports.
No comments in code unless the user asks or the code is genuinely unexplainable without one; documentation lives in docs/ and JSDoc-free exported types.
Prefer small pure functions for scoring/ranking logic so they stay unit-testable and deterministic (inject clocks where time matters).

Read the full file on GitHub · 77 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 · 77 lines · 894 tokens per session scan A e6f53ddafc52

Subscribe to this mod's changes

mcp-nexus AGENTS.md is an instructions file published in the GitHub repository fyrlabs/mcp-nexus (0 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 894 tokens to every session, about $0.0036 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 2026-08-31.

mcp-nexus AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-nexus AGENTS.mdfyrlabs/mcp-nexus	Instructions file	0	2mo ago	Apache-2.0	A	894	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

mcp-nexus: Instructions file for Codex