What is nexus-exchange-mcp AGENTS.md?

A contribution guide for a Model Context Protocol server, which exposes an API as tools an agent can call.

It is for checking changes before pushing, structuring pull requests, requiring the right approvals, and keeping network host mappings and private-stage details correct.

It records review, pull-request, testing, and API rules that help prevent unsafe merges and incorrect network or funds-related behavior.

How nexus-xyz/nexus-exchange-mcp configures Codex and OpenCode

Reuse

Borrowing it

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

Clone the repo

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

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

Your own site

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

Per session 684 This file is loaded in full into every session.

When invoked 684 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	$0.00684	$0.00684
Opus 5	$0.00342	$0.00342
Sonnet 5	$0.00137	$0.00137
Haiku 4.5	$0.00068	$0.00068

Measured 10d ago against content hash 234a51f6ca22, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

nexus-exchange-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 10d 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 · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Contributing guide — nexus-exchange-mcp

The Model Context Protocol server exposing the Nexus Exchange API as agent tools.

Merging

Don't merge a PR without an approving review — CI passing isn't a substitute.
Don't merge a PR you didn't author without an approving review and the author's sign-off. Check the author first (gh pr view <n> --json author,reviewDecision).
Re-approval isn't needed for follow-up commits to an already-approved PR.

Pull requests

One concern per PR; link its tracking issue (ENG-XXXX) in the title.
Respond to review comments before merging.

Checks (before pushing)

The repo's lint, typecheck, and test scripts all pass — CI enforces these.

API contract

The network → host map lives in exactly one file, src/networks.ts, copied from the spec's x-nexus-networks. Never interpolate a host from a network name (mainnet is api.nexus.xyz, not api.mainnet.nexus.xyz), and never let an unrecognized network fall back to a default — it is treated as real funds.
No hostname for a private stage belongs in this repo — not in source, docs, tests, commit messages or PR bodies, and neither does the stage taxonomy that names them. Point custom at them instead (ENG-9823). Illustrate with RFC 2606 reserved names (example.com in docs, example.invalid in tests) and generic labels (dev, example).
custom is client-side only: it is not a value the API accepts and must never appear in x-nexus-networks, so it is deliberately not in NETWORK_IDS or NETWORKS. Its funds are a tri-state (real | play | unknown) that a caller declares; match play positively in a guard, never !== "real", or unknown falls through as if it were safe. A tool that cannot be undone declares fundsGuard and is refused on an undeclared target.
Keep the pinned nexus-exchange-api version in sync when the spec bumps. spec-autobump opens that PR for you and labels it breaking or not; merging it is a human decision, and spec-drift on that PR is the check that says whether it needs code changes.
New API capabilities should be surfaced as MCP tools so an agent can use them.
Every tool declares the spec operations it calls in its ops field — required by the type, verified against the handler by scripts/check_spec_drift.py, and the source endpoints.txt is generated from. Run npm run spec:drift after touching a tool, and npm run spec:drift:write if the operation set moved.
Coverage is reported in two units and they are not interchangeable: registered tools (MCP's own axis) and spec operations (comparable with the other SDKs). Never report the tool count as a coverage figure. See docs/coverage-unit.md.

Read the full file on GitHub · 51 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.

10d ago First seen · 51 lines · 684 tokens per session scan A 234a51f6ca22

Subscribe to this mod's changes

nexus-exchange-mcp AGENTS.md is an instructions file published in the GitHub repository nexus-xyz/nexus-exchange-mcp (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 684 tokens to every session, about $0.0034 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.

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

nexus-exchange-mcp: Instructions file for Codex