ontology-atlas: Instructions file for Codex

AGENTS.md

ontology-atlas AGENTS.md is an instructions file for Codex, OpenCode from wlsdks/ontology-atlas. It costs 2,704 tokens per session, scanned A, original, MIT.

The main contributor guide for Ontology Atlas, a local-first codebase map that connects product meaning with implementation evidence. It explains the project’s architecture, file structure, routes, operating checks, and supporting tools.

In plain words
What is it for?
Use it as the starting point for changes to Ontology Atlas, including its Markdown knowledge graph, Git-based workflow, agent interfaces, documentation, routes, and required development checks.
Why use it?
It gives people and coding agents the project’s non-negotiable rules before they make changes. It also explains how Atlas complements code search and indexes by preserving durable meaning, evidence, impact boundaries, and verification paths.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions AGENTS.md.

This is wlsdks/ontology-atlas's own configuration. It tells Codex and OpenCode how to work on ontology-atlas itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ontology-atlas configures →

Reuse

Borrowing it

Nothing to install: this file belongs to wlsdks/ontology-atlas. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/wlsdks/ontology-atlas/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/wlsdks/ontology-atlas

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for ontology-atlas AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/wlsdks/ontology-atlas/agents-md/github.svg)](https://agentmods.dev/instructions/wlsdks/ontology-atlas/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/wlsdks/ontology-atlas/agents-md"><img src="https://agentmods.dev/badge/instructions/wlsdks/ontology-atlas/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ontology-atlas AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/wlsdks/ontology-atlas/agents-md"><img src="https://agentmods.dev/badge/instructions/wlsdks/ontology-atlas/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,704 This file is loaded in full into every session.
When invoked 2,704 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.02704 $0.02704
Opus 5 $0.01352 $0.01352
Sonnet 5 $0.00541 $0.00541
Haiku 4.5 $0.00270 $0.00270

Measured yesterday against content hash b9211e5bd371, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ontology-atlas 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 yesterday.

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 · 206 lines

How it starts

The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — ontology-atlas

Canonical contributor guide for people and AI agents. Read it before changing the repository; use the linked authority for detail rather than duplicating it.

Product and non-negotiable architecture

Ontology Atlas is a local-first codebase ontology for understanding what code builds, why it is structured that way, and what changes affect, across product meaning and implementation evidence. Vault Markdown frontmatter is the graph; Git is the source of truth, and people judge meaning through files and diffs. Agents use the same vault through MCP/CLI. The macOS app carries its MCP server; source checkouts run it directly. There is no npm package.

Atlas complements CodeGraph, grep, AST indexes, language servers, and source search. Those tools answer structural questions; Atlas provides the durable meaning layer: task starting point, domain/capability context, evidence, impact boundary, and verification path.

The public meta-model belongs only in docs/ONTOLOGY-ATLAS-SPEC.md §2/§5. Do not create competing kind or relation glossaries. The product is agent-native and human-sovereign: every surface must be consumable as typed facts by an agent and readable and judgeable by a human.

The app is the vault's home and the web is a gateway or second-best workbench. They share one folder, parser contract, and vault-local records; they do not promise identical screens. Keep degradation honest.

One codebase ontology, maintained by people and AI agents.

No backend, login, auth provider, environment setup, seed data, API routes, or server actions belong here. output: 'export' is intentional.

Start here

pnpm install && pnpm dev
pnpm --dir mcp install
pnpm checks:changed

Re-run pnpm --dir mcp install after a pull changes mcp/package.json; root installation does not update mcp/node_modules. Start verification with pnpm checks:changed; -- --run runs every recommendation and stops at the first failure. Do not hand-pick its list.

Read the full file on GitHub · 206 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. yesterday Changed · +14 tokens per session b9211e5bd371
  2. 2d ago Changed · +6 tokens per session 562d05ce228c
  3. 3d ago Changed · +1 lines · -1 tokens per session 1af112ab7dd5
  4. 5d ago Changed 15237e77b1fd
  5. 10d ago First seen · 205 lines · 2,685 tokens per session scan A 5410aa7fcb3b

Subscribe to this mod's changes

ontology-atlas AGENTS.md is an instructions file published in the GitHub repository wlsdks/ontology-atlas (100 stars, last pushed yesterday), licensed MIT. It adds 2,704 tokens to every session, about $0.0135 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

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

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 · 5,153 tokens

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

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

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 · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens