nexus-mcp: Instructions file for Claude Code

CLAUDE.md

nexus-mcp CLAUDE.md is an instructions file for Claude Code from jaggernaut007/nexus-mcp. It costs 3,011 tokens per session, scanned A, original, MIT.

A project instruction file for Nexus-MCP, a local server that combines code search, a map of code relationships, and stored project notes. It tells the agent how to explore an indexed codebase and documents known limits.

In plain words
What is it for?
Use it when indexing a repository, searching code, locating symbols, tracing callers, explaining code, analyzing a project, or retrieving stored notes.
Why use it?
It helps the agent find relevant code and relationships through the project's own tools before falling back to basic file search. This reduces guesswork when navigating a large codebase.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: mentions Claude Code.

This is jaggernaut007/nexus-mcp's own configuration. It tells Claude Code how to work on nexus-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything nexus-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jaggernaut007/nexus-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/jaggernaut007/nexus-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/jaggernaut007/nexus-mcp

Made for: Claude Code.

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.

agentmods badge for nexus-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jaggernaut007/nexus-mcp/claude-md.svg)](https://agentmods.dev/instructions/jaggernaut007/nexus-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jaggernaut007/nexus-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/jaggernaut007/nexus-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,011 This file is loaded in full into every session.
When invoked 3,011 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.03011 $0.03011
Opus 5 $0.01505 $0.01505
Sonnet 5 $0.00602 $0.00602
Haiku 4.5 $0.00301 $0.00301

Measured 6d ago against content hash 46f92cf284bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

nexus-mcp CLAUDE.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 6d 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.

CLAUDE.md · 192 lines

How it starts

The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Nexus-MCP

Unified MCP server: hybrid search + code graph + semantic memory. Target: <350MB RAM.

Use Nexus-MCP Tools Before Built-in Tools

Nexus-MCP is registered as an MCP server (nexus-mcp-ci) with 10 tools: index, status, health, search, find_symbol, graph, explain, analyze, map, memory. Prefer these over Read/Grep/Glob for exploring an indexed codebase — start with status, index if needed, then search/find_symbol/graph before falling back to built-in tools for files nexus-mcp has already identified.

Full workflow guidance, the tool reference table, and best practices live in the nexus-mcp skill, not here — that content changes per-task and belongs in on-demand skill context, not an always-loaded block in this file. Install it via:

/plugin marketplace add jaggernaut007/Nexus-MCP
/plugin install nexus-mcp@nexus-mcp

(Requires pip install nexus-mcp-ci first — the plugin registers the MCP server, it doesn't install the Python package.) See plugin/skills/nexus-mcp/SKILL.md in this repo to read the skill content directly.

Known limitations

  • The call graph only sees static edges. graph() (both direction="callers"/ "callees" and transitive=True) is built from tree-sitter + ast-grep parsing, not runtime tracing. It will miss: dynamic dispatch (Python monkey-patching, Ruby metaprogramming), calls made through callbacks/closures/lambdas (e.g. .map(lambda x: foo(x)) shows no edge to foo), and reflection-based calls. Treat graph(transitive=True) results as a lower bound on blast radius, not an exhaustive one — especially in highly dynamic languages (Python, Ruby) or callback-heavy code (JS/TS).
  • Graph fidelity varies by language. Python, JavaScript/TypeScript, C/C++, Go, and Java get full call-graph edges (both tree-sitter symbols and ast-grep structure). Rust, Ruby, PHP, Swift, C#, Scala, Lua, and Dart get ast-grep structural parsing but weaker symbol-level precision. Bash gets tree-sitter symbols only — no call graph.
  • Auto-reindex has a detection lag, not a guarantee of freshness. With NEXUS_AUTO_WATCH enabled (default), edits are picked up after a debounce window (a few seconds); status()/search() additionally run a throttled staleness check (see NEXUS_STALENESS_CHECK_INTERVAL, default 15s) as a safety net. Between an edit and the next debounce/throttle window, search results can reflect slightly stale code — this is a bounded window, not silent indefinite staleness.

Read the full file on GitHub · 192 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.

  1. 6d ago First seen · 192 lines · 3,011 tokens per session scan A 46f92cf284bc

Subscribe to this mod's changes

nexus-mcp CLAUDE.md is an instructions file published in the GitHub repository jaggernaut007/nexus-mcp (0 stars, last pushed 12d ago), licensed MIT. It adds 3,011 tokens to every session, about $0.0151 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.

Related

Other instructions, from other repositories

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 · 5,182 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

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).

microsoft/vscode · 5,001 tokens

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

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.

langchain-ai/langchain · 4,469 tokens

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.

github/spec-kit · 7,104 tokens