agentmods.dev

agentic-os AGENTS.md

A set of instructions for developing the Agentic OS Console, a Next.js web application that connects to a locally running Hermes Agent. It explains the repository's source documents, technology, structure, and purpose.

In plain words
What is it for?
Use it when working on the referenced Agentic OS Console repository, including its Next.js, TypeScript, Tailwind, and local database code.
Why use it?
It tells coding agents which documents and project conventions to follow when changing the console codebase.

Instructions file for CodexOpenCode

11 4mo ago A scan 1,655 tokens original MIT
View the source file aporb/agentic-os
Install

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.

agentmods
npx agentmods add instructions/aporb/agentic-os/agents-md
Clone the repo
git clone --depth 1 https://github.com/aporb/agentic-os

Made for: Codex, OpenCode.

Per session 1,655 This file is loaded in full into every session.
When invoked 1,655 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.01655 $0.01655
Opus 5 $0.00827 $0.00827
Sonnet 5 $0.00331 $0.00331
Haiku 4.5 $0.00166 $0.00166

Measured 2d ago against content hash f78c75a1263d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentic-os 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.

AGENTS.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Working on the Agentic OS Console codebase

Instructions for AI agents (Claude Code, Cursor, Copilot, etc.) helping develop this codebase. End users don't read this file — they install via Hermes per the README.

What this repo is

A Next.js 15 (App Router) web app that turns Hermes Agent into an AI-native operating system for solo founders. MIT-licensed lead-gen funnel for the paid Kodax appliance.

Not a SaaS. Not a chat app. Not a markdown-only template. The Console is a real Next.js application that talks to a locally-running Hermes via its api_server gateway platform.

Source-of-truth documents (read first)

  • wiki/draft-agentic-os-spec.md — full product spec. §10 has the positioning rules. §3 has the file tree. §6 has the bridge architecture.
  • wiki/draft-skill-pack-design.md — 73-skill C-suite catalog. Migration map at Appendix B.
  • wiki/draft-build-plan.md — execution plan for v1.
  • wiki/methodology.md — the philosophy essay (also linked from the user-facing README).

Tech stack

  • Next.js 15 App Router · TypeScript · Tailwind · shadcn-style local components (no CLI dep)
  • better-sqlite3 for vault.db reads
  • gray-matter + remark for markdown parsing
  • lucide-react for icons
  • No Radix beyond what shadcn primitives use; no heavy component libraries
  • Python 3.11+ for the indexer (scripts/index_vault.py) and vector search (scripts/search_vectors.py)

File layout (load-bearing parts)

app/                    Next.js routes (pages + API)
  api/                  REST endpoints; all require validateToken()
  page.tsx              Home dashboard
  skills/               Pack browser, runner
  wiki/                 Tree + page reader/editor
  sources/              Drag-drop ingest
components/
  ui/                   Local shadcn-style primitives (Button, Card, Input, …)
  home/, skills/, wiki/, sources/   Surface-specific components
lib/
  config.ts             Reads ~/.hermes/agentic-os/config.json
  auth.ts               Ephemeral token, localhost-bound
  vault.ts              Read/write markdown with frontmatter; zone access rules
  hermes.ts             Hermes API client (status, sessions, crons, runSkill stream)
  search.ts             Web search via ddgr → gogcli → browser fallback
  updater.ts            Semver check + applyUpdate
  packs.ts              Pack metadata + UI labels
  skills.ts             Server-side skill loader (shipped + vault overrides)
hermes/
  install.sh            Bootstrap script Hermes runs for the user
  start.sh, stop.sh, doctor.sh
  persona-template.md   Generic founder-friendly default
  bridge/               Hermes skill bundle (install/start/stop/update/doctor/vault-discover/cron-register/skill-register)
  skills/               Shipped skill packs (ceo/, cro/, cmo/)
scripts/
  index_vault.py        SQLite FTS5 + vector indexer
  search_vectors.py     Cosine similarity query helper

Read the full file on GitHub · 144 lines

Changes

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.

  1. 2d ago First seen · 144 lines · 1,655 tokens per session scan A f78c75a1263d

Subscribe to this mod's changes

agentic-os AGENTS.md is an instructions file published in the GitHub repository aporb/agentic-os (11 stars, last pushed 4mo ago), licensed MIT. It adds 1,655 tokens to every session, about $0.0083 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.

Building agents
Related

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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.

openai/codex · 5,182 tokens

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.

langchain-ai/langchain · 4,345 tokens

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).

microsoft/vscode · 5,001 tokens

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.

vercel/next.js · 7,296 tokens