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/fyrlabs/mcp-nexus/agents-mdgit clone --depth 1 https://github.com/fyrlabs/mcp-nexusWrote 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/fyrlabs/mcp-nexus/agents-md)<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="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 5.1 | $0.00894 | $0.00894 |
| Opus 5 | $0.00447 | $0.00447 |
| Sonnet 5 | $0.00179 | $0.00179 |
| Haiku 4.5 | $0.00089 | $0.00089 |
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 5d 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.
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 ismcp-nexus-product-spec.mdat the repo root; treat it as the architecture reference. - Runtime: TypeScript ESM on Node.js
>= 22.13(first Node line wherenode:sqliteis 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 insrc/tests/and mirror the source tree (e.g.src/router/ranker.ts→src/tests/router/ranker.test.tsor a matching<area>/<area>.test.tsfile). Shared test helpers go insrc/tests/helpers/. - Public API is only what
src/index.tsexports. 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 typefor type-only imports,.jsextensions 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).
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.
- 5d ago First seen · 77 lines · 894 tokens per session scan A e6f53ddafc52
mcp-nexus AGENTS.md is an instructions file published in the GitHub repository fyrlabs/mcp-nexus (0 stars, last pushed 11d ago), licensed Apache-2.0. It adds 894 tokens to every session, about $0.0045 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
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.