companyos: Instructions file for Codex

AGENTS.md

companyos AGENTS.md is an instructions file for Codex, OpenCode from tomevault-io/companyos. It costs 1,046 tokens per session, scanned A, original, MIT.

A set of instructions for AI coding agents working on CompanyOS, an AI-operated company project. It explains the project's skills, repeatable commands and governing documents.

In plain words
What is it for?
Use it to guide agents while they diagnose issues, run repository procedures and prepare decisions or changes. It is documentation, not a software feature.
Why use it?
It gives agents project context and tells them to investigate problems before acting, reducing uninformed changes or proposals.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is tomevault-io/companyos's own configuration. It tells Codex and OpenCode how to work on companyos 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 companyos configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tomevault-io/companyos. 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/tomevault-io/companyos/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/tomevault-io/companyos

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 companyos AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/tomevault-io/companyos/agents-md/github.svg)](https://agentmods.dev/instructions/tomevault-io/companyos/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/tomevault-io/companyos/agents-md"><img src="https://agentmods.dev/badge/instructions/tomevault-io/companyos/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 companyos AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/tomevault-io/companyos/agents-md"><img src="https://agentmods.dev/badge/instructions/tomevault-io/companyos/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,046 This file is loaded in full into every session.
When invoked 1,046 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 $0.01046 $0.01046
Opus 5 $0.00523 $0.00523
Sonnet 5 $0.00209 $0.00209
Haiku 4.5 $0.00105 $0.00105

Measured 8d ago against content hash 7bfe7da50957, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

companyos 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 8d 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 · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Operating instructions for an AI-instructed company

Root agent context. Loaded at the start of every session. Universal — works for any company. Project-specific overrides go in a sibling file your tool reads alongside this one.

What this company runs on

Three layers:

  1. Skills at skills/ — patterns the agent loads when the named situation arises. Don't re-invent these patterns from session memory; load the file.
  2. A justfile at the repo root — discoverable commands for repeatable runbooks. just --list shows the surface.
  3. Constitutional documents in constitutions/ (operator-owned, agent-read-only) — strategy, design principles, non-goals. Agents propose amendments; operators ratify by editing the canonical file.

The three layers compose. Skills inform judgment, justfile recipes execute deterministic procedures, constitutions hold the strategic invariants. Don't conflate them.

Default behaviours

These are the defaults that operate underneath everything else. Project-specific overrides may extend or refine.

Diagnose before acting

Under operator pressure (alert pasted, "fix this", urgency), the first move is read-only investigation, not the implied fix. The pattern lives in skills/diagnose-before-acting.md. The cost of pausing is small; the cost of an obvious-wrong fix is hours.

Decision memos before non-trivial proposals

Anything cross-cutting, schema-touching, externally-visible, or where two valid approaches exist gets a memo first. Format in skills/decision-memo.md. The memo is the decision aid, not the decision.

Pre-ship adversary on every non-trivial commit

Before git commit, run the four attacks: scope creep, failure modes, rollback, shipping-gate simulation. Two-to-three minutes. skills/pre-ship-adversary.md.

Vocabulary discipline on every external string

Emails, landing copy, READMEs, CLI output, error messages. The list lives in your project's vocabulary file; the discipline lives in skills/vocabulary-check.md.

Read the full file on GitHub · 80 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. 8d ago First seen · 80 lines · 1,046 tokens per session scan A 7bfe7da50957

Subscribe to this mod's changes

companyos AGENTS.md is an instructions file published in the GitHub repository tomevault-io/companyos (2 stars, last pushed 2mo ago), licensed MIT. It adds 1,046 tokens to every session, about $0.0052 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.

Related

Other instructions, from other repositories

ai-agent-rules-generator ui-design.instructions.md

Glitch Payment Gateway admin UI design rules — mandatory element & component reference for WooCommerce settings.

savedpixel/ai-agent-rules-generator · 701 tokens

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