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/profsynapse/nexus/claude-mdgit clone --depth 1 https://github.com/ProfSynapse/nexusWhat 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 | $0.01259 | $0.01259 |
| Opus 5 | $0.00629 | $0.00629 |
| Sonnet 5 | $0.00252 | $0.00252 |
| Haiku 4.5 | $0.00126 | $0.00126 |
Grade A, and why
nexus 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 2d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nexus
Obsidian community plugin (claudesidian-mcp, manifest id nexus) that exposes the
vault to AI agents over MCP. TypeScript, esbuild, Obsidian Plugin API, MCP SDK.
isDesktopOnly: false — this plugin runs on mobile.
Hard rules
- Never top-level import Node built-ins or npm packages with Node deps — mobile
has no
fs/path/stream/events. Top-level imports run before anyPlatform.isDesktopguard. UsedesktopRequire()orawait import()inside a function. - Styles in
styles.css, never inline. NoinnerHTMLwith dynamic content.registerDomEvent, neveraddEventListener. requestUrl(), notfetch().normalizePath()for paths — and note it does not strip.., so confinement needs an explicit guard.- Never hardcode storage roots (
Nexus,.nexus) — resolve from settings. - Tool parameter schemas are documentation, not validation. There is no ajv behind them; guards belong in the service/normalizer layer.
Layout
| Path | Contents |
|---|---|
src/agents/ |
Agents and their tools (apps/ = opt-in app agents) |
src/services/ |
LLM providers, memory, conversations, chat, agent registration |
src/database/ |
Storage adapters, SQLite cache, migrations |
src/ui/, src/components/, src/settings/ |
Chat view, modals, settings tabs |
src/main.ts, src/connector.ts |
Plugin entry point; MCP connector |
docs/plans/ |
Design plans — the format to follow for new ones |
docs/changelog.md |
Release history |
Architecture in five lines
- Agent-Tool pattern. Agents extend
BaseAgentand register tools extendingBaseTool<Params, Result>. Results are{ success, ...data }or{ success: false, error }. - MCP exposes exactly two tools —
getTools(discovery) anduseTools(execution). Every other agent is internal. - Storage is hybrid: sharded JSONL event store is the source of truth, SQLite is a rebuildable cache.
- Services are singletons with constructor injection.
- The AI never gets a destructive delete — it gets
archive, which is reversible. Permanent delete is UI-only.
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.
- 2d ago First seen · 101 lines · 1,259 tokens per session scan A b43a1fbbe320
nexus CLAUDE.md is an instructions file published in the GitHub repository ProfSynapse/nexus (154 stars, last pushed 2d ago), licensed MIT. It adds 1,259 tokens to every session, about $0.0063 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 2026-08-30.
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.