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/aporb/agentic-os/claude-mdgit clone --depth 1 https://github.com/aporb/agentic-osWrote 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/aporb/agentic-os/claude-md)<a href="https://agentmods.dev/instructions/aporb/agentic-os/claude-md"><img src="https://agentmods.dev/badge/instructions/aporb/agentic-os/claude-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 | $0.00445 | $0.00445 |
| Opus 5 | $0.00222 | $0.00222 |
| Sonnet 5 | $0.00089 | $0.00089 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
agentic-os 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 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
CLAUDE.md — for Claude Code working on this repo
This is a pointer file. The full developer-facing instructions live in AGENTS.md. Read that first.
Quick context for Claude Code
- What: Next.js 15 web app that turns Hermes Agent into an AI-native operating system for solo founders.
- Audience: End users install via Hermes (
> install agentic-os from github.com/aporb/agentic-os); they don't read this file. THIS file is for AI agents helping develop the codebase. - Source of truth:
wiki/draft-agentic-os-spec.mdfor product,wiki/draft-skill-pack-design.mdfor skills,wiki/draft-build-plan.mdfor execution plan,wiki/methodology.mdfor philosophy.
Voice and vocabulary (strict)
- USE: leverage, own, compete, coordination overhead, second brain, pipeline, runway, retention
- AVOID: productivity, efficient, automate, seamless, AI workforce, AI company, founding cohort, named-character mascots, em-dash abuse, hedging language ("we think," "you might find"), corporate jargon
Apply these rules in:
- README, AGENTS.md, any user-facing copy
- All shipped skill files in
hermes/skills/ - UI strings, button labels, empty states
Don't
- Don't add a chat surface to the Next.js app — Hermes already has chat
- Don't introduce paid search APIs (Tavily / Perplexity / Bing) — use the
ddgr→gogcli→ browser cascade inlib/search.ts - Don't add paid-tier feature flags — Kodax features live in a separate private repo
- Don't push to git remote unless the user asks
- Don't anthropomorphize with named character agents — the persona system is user-customizable
Working scripts
npm install
npm run dev # localhost:18443
npm run typecheck # tsc --noEmit
npm run build # production build smoke test
See AGENTS.md for full conventions.
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 · 39 lines · 445 tokens per session scan A 87ab6d990853
agentic-os CLAUDE.md is an instructions file published in the GitHub repository aporb/agentic-os (11 stars, last pushed 4mo ago), licensed MIT. It adds 445 tokens to every session, about $0.0022 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.