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/jaggernaut007/nexus-mcp/agents-mdgit clone --depth 1 https://github.com/jaggernaut007/nexus-mcpWrote 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/jaggernaut007/nexus-mcp/agents-md)<a href="https://agentmods.dev/instructions/jaggernaut007/nexus-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/jaggernaut007/nexus-mcp/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 | $0.00526 | $0.00526 |
| Opus 5 | $0.00263 | $0.00263 |
| Sonnet 5 | $0.00105 | $0.00105 |
| Haiku 4.5 | $0.00053 | $0.00053 |
Grade A, and why
nexus-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 4d 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.
What it actually says
Nexus-MCP Agent Guidelines
Architecture
Single MCP server consolidating CodeGrok + code-graph-mcp. 15 tools, <350MB RAM.
Stack
- LanceDB: vectors + FTS (replaces ChromaDB)
- ONNX Runtime: inference (replaces PyTorch)
- bge-small-en: default embedding model (50MB)
- rustworkx: in-memory directed graph
- tree-sitter + ast-grep: dual parsing
Key Constraints
- Python 3.10, 3.11, or 3.12 (Python 3.13+ is not yet supported by tree-sitter-languages)
- pip (comes with Python)
- All modules lazy-import heavy deps
- Models unloaded after indexing (
del model; gc.collect()) - Batch embedding size=32
- Graph payloads: {id, name, type, file, line} only
Testing
- Tests first (spec-driven)
pytest -vfor all testsruff check .must pass- Target: 140+ tests by Phase 5
Code Style
- ruff for linting (line-length=100)
- Frozen dataclasses for immutable models
- ABC interfaces for swappable components
- Thread-safe singletons with locks
Cross-harness compatibility
AGENTS.md is the single source of truth for every agent harness driving this repo. Per-tool bridges:
- Claude Code →
CLAUDE.md+.claude/rules/ - Codex CLI → reads this file natively (keep it lean)
- Cline →
.clinerules/00-source-of-truth.md; no parallel Memory Bank - Antigravity CLI →
GEMINI.mdthin bridge, speculative until its discovery mechanism is documented Durable rules go here (portable) — never into a tool-specific file.
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.
- 4d ago First seen · 44 lines · 526 tokens per session scan A 2269bea48fe7
nexus-mcp AGENTS.md is an instructions file published in the GitHub repository jaggernaut007/nexus-mcp (0 stars, last pushed 10d ago), licensed MIT. It adds 526 tokens to every session, about $0.0026 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
roam-code AGENTS.md
AGENTS.md instructions for Cranot/roam-code, covering agents.md — roam-code development guide, what this project is, documentation hub, where files go (private vs public) and quality discipline (from internal/dogfood/ + agi-in-md).
VibeDrift AGENTS.md
AGENTS.md instructions for VibeDrift/VibeDrift, covering vibedrift — agent & contributor guide, core identity (read this first), stack, commands and architecture.
agentmap AGENTS.md
Instructions for raymondchins/agentmap, covering agentmap — project instructions, ⚠️ this is a public oss repo, not one of ray's apps, read before editing, layout and hard invariants.
dekko CLAUDE.md
Claude Code instructions for aahlijia/dekko, covering claude.md, what this project is, working in this repo and evaluation reports: test-repos/reports/.
codemap AGENTS.md
AGENTS.md instructions for stainless-code/codemap, a project described as: Cut AI-agent token waste 90% — query a local SQLite structural index of your JS/TS/CSS codebase with SQL in one round-trip instead of 3–5 file reads. Symbols, imports, calls, components, CSS tokens, coverage, markers. CLI, MCP (21 tools), HTTP…
coograph CLAUDE.md
Instructions for paullukic/coograph, covering claude code instructions, pre-flight (run on every session start), communication style, quick reference and branching strategy.