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/asimons81/nexusos/agents-mdgit clone --depth 1 https://github.com/asimons81/nexusosWrote 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/asimons81/nexusos/agents-md)<a href="https://agentmods.dev/instructions/asimons81/nexusos/agents-md"><img src="https://agentmods.dev/badge/instructions/asimons81/nexusos/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 | $0.01779 | $0.01779 |
| Opus 5 | $0.00890 | $0.00890 |
| Sonnet 5 | $0.00356 | $0.00356 |
| Haiku 4.5 | $0.00178 | $0.00178 |
Grade A, and why
nexusos 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.
How it starts
The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file defines the operating contract for AI coding agents working on NexusOS. Read it before inspecting tasks, editing code, or changing documentation.
Mission
NexusOS is a local-first knowledge operating system for AI agents. The v0.1 release must provide a small, deterministic, well-tested memory contract over files the user owns.
The repository is shipping stable v0.1.0. The planned core v0.1 feature scope
shipped through the alpha/RC train. Preserve the frozen v0.1 contracts and route
new product scope to the next release train.
The executable release plan lives in ROADMAP.md.
Isolation rules
These are non-negotiable:
- Work only inside the NexusOS project directory.
- Namespace all product state under CLI
nexusos, packagenexusos, environment variablesNEXUSOS_*, and workspace state.nexusos/. - Never reference, import, inspect, or depend on private Nexus projects or personal knowledge stores.
- Never hardcode personal names, paths, domains, credentials, or workspace content.
- Tests must use synthetic fixtures and temporary directories.
- Source documents are immutable unless a future, explicitly approved write system is implemented. v0.1 has no source-mutation feature.
- Derived state must remain disposable and rebuildable from source files.
Architecture boundary
core (errors, models, path safety, configuration)
↓
workspace (initialization, identity, templates)
↓
indexing (discovery, parsing, graph, schema, migrations, database, lock, kernel)
↓
services (doctor, index, status, search, navigation, lint, serve, demo)
↓
cli (Typer and Rich adapters)
mcp (top-level adapter beside cli, importing services only)
Rules:
coremust not import Typer, Rich, MCP, CLI, or service modules.workspacemay depend oncore, never on CLI or MCP.indexingmay depend oncoreandworkspace, never on CLI or MCP.servicesowns reusable application behavior.cliformats command input and output around services.mcpis a top layer. It imports services, not indexing internals or CLI code.- CLI and MCP behavior should share service contracts rather than duplicate logic.
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 · 203 lines · 1,779 tokens per session scan A b6fc1dbec418
nexusos AGENTS.md is an instructions file published in the GitHub repository asimons81/nexusos (19 stars, last pushed 9d ago), licensed Apache-2.0. It adds 1,779 tokens to every session, about $0.0089 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
memory-forest AGENTS.md
AGENTS.md instructions for hyungchulc/memory-forest, covering repository contract, scope, invariants and change discipline.
markdown-vault-mcp AGENTS.md
AGENTS.md instructions for pvliesdonk/markdown-vault-mcp, covering markdown vault mcp, design, project structure, conventions and skills.
my-wiki AGENTS.md
Instructions for NimaChu/my-wiki, covering my wiki agent project, project map, knowledge model, route requests and development checks.
basic-memory CLAUDE.md
Claude Code instructions for basicmachines-co/basic-memory, a project described as: AI conversations that actually remember. Never re-explain your project to your AI again. Join our Discord: https://discord.gg/tyvKNccgqN.
scraps CLAUDE.md
Claude Code instructions for boykush/scraps, covering scraps development with claude code, project structure and development workflow.
scratchpad CLAUDE.md
Claude Code instructions for NikiforovAll/scratchpad, covering what this is, commands, monorepo layout, architecture and viewer (src/ui/).