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/kksudo/agentfs/agents-mdgit clone --depth 1 https://github.com/kksudo/AgentFSWhat 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 | $0.02498 | $0.02498 |
| Opus 5 | $0.01249 | $0.01249 |
| Sonnet 5 | $0.00500 | $0.00500 |
| Haiku 4.5 | $0.00250 | $0.00250 |
Grade A, and why
AgentFS 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 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 — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentFS — Instructions for AI Agents
This file contains instructions for AI agents (Claude Code, Cursor, OpenClaw, etc.) working on the AgentFS project.
Project Overview
AgentFS is a CLI tool (npx create-agentfs) that scaffolds an Obsidian vault as a filesystem-based operating system for AI agents. The core concept: a .agentos/ kernel space serves as single source of truth and compiles into native agent config formats.
Status: v0.1.4 — All 13 epics implemented (Phases 1–11 complete). See docs/architecture.md for the full spec.
Repository Structure
AgentFS/
├── AGENTS.md ← This file (agent instructions for all runtimes)
├── CLAUDE.md ← Includes @AGENTS.md (Claude Code entry point)
├── .cursorrules ← Cursor agent entry point (includes this file)
├── README.md ← Project overview and roadmap
├── CONTRIBUTING.md ← Contribution guidelines
├── LICENSE ← MIT license
├── package.json ← create-agentfs (Node.js >= 24.0.0, ESM)
├── tsconfig.json ← TypeScript strict, ES2022, NodeNext
├── tsconfig.test.json ← Extends tsconfig for Jest + ESM
├── jest.config.js ← Jest with ts-jest ESM preset
├── eslint.config.js ← ESLint flat config with @typescript-eslint
├── docs/
│ ├── architecture.md ← Full architecture spec (v3, 17 sections) — THE source of truth
│ ├── internals.md ← Implementation reference (memory, boot, security, FHS)
│ ├── quickstart.md ← Human quick start guide
│ └── ai-manual.md ← AI agent manual for vault interaction
├── src/
│ ├── cli.ts ← CLI entry point (subcommand router)
│ ├── index.ts ← Public API barrel (re-exports main, VERSION)
│ ├── types/ ← Core interfaces (Manifest, AgentCompiler, SecurityPolicy, Memory, Setup)
│ ├── utils/ ← Utilities (fhs-mapping)
│ ├── generators/ ← Scaffold generators (filesystem, manifest, init, ignore, memory, prompts)
│ ├── compilers/ ← Compile drivers (base, claude, openclaw, cursor, agent-map)
│ ├── commands/ ← CLI subcommands (compile, onboard)
│ ├── memory/ ← Memory system (parser, confidence, episodic, procedural)
│ ├── security/ ← Security subsystem (policy parser, AppArmor profiles)
│ ├── secrets/ ← Secrets management (SOPS/age, exfil guard)
│ ├── cron/ ← Cron jobs (consolidation, distillation, triage, heartbeat)
│ ├── sync/ ← Sync & import (memory sync, drift detection)
│ ├── profiles/ ← Profile generators (personal, company, shared)
│ └── modules/ ← Optional modules (career, content, engineering)
├── templates/
│ └── compilers/ ← Handlebars templates (claude.md.hbs, agent-map.md.hbs)
├── tests/ ← Jest tests (261+ tests across 18 suites)
└── _bmad/ ← BMAD Method tooling (skills, planning artifacts)
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 · 223 lines · 2,498 tokens per session scan A d860a25f4167
AgentFS AGENTS.md is an instructions file published in the GitHub repository kksudo/AgentFS (2 stars, last pushed 4mo ago), licensed MIT. It adds 2,498 tokens to every session, about $0.0125 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.
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.