What is solo-compay-os AGENTS.md?

Repository instructions for building a readable, runnable reference implementation of a one-person company operated by an AI agent.

They guide work on the command-line interface, mock-provider runs, skill discovery, structured outputs, replayable run data, and tests.

They set shared rules for reliable runs, strict JSON results, trace records, and a simple project structure.

How hubo0520/solo-compay-os configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to hubo0520/solo-compay-os. 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/hubo0520/solo-compay-os/master/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/hubo0520/solo-compay-os

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/hubo0520/solo-compay-os/agents-md/github.svg)](https://agentmods.dev/instructions/hubo0520/solo-compay-os/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/hubo0520/solo-compay-os/agents-md"><img src="https://agentmods.dev/badge/instructions/hubo0520/solo-compay-os/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/hubo0520/solo-compay-os/agents-md"><img src="https://agentmods.dev/badge/instructions/hubo0520/solo-compay-os/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 762 This file is loaded in full into every session.

When invoked 762 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.

Model	Per session	Once invoked
Fable 5.1	$0.00762	$0.00762
Opus 5.5	$0.00305	$0.00305
Sonnet 5.5	$0.00152	$0.00152
Haiku 4.5	$0.00076	$0.00076

Measured 2mo ago against content hash eab427240548, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

solo-compay-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 2mo 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 · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file is written for AI coding agents (and humans) contributing to this repository.

Goal: keep this repo a teaching-quality reference implementation of an "agent one-person company" that is runnable, readable, and easy to extend.

Core principles

Runnable first
- solo-company run "..." --provider mock must always work without any keys.
- CI should run end-to-end using MockProvider.
Progressive disclosure
- Skills are discovered by metadata first (frontmatter), then instructions, then resources.
- Do not load all skill bodies into context unless necessary.
Structured outputs
- Any LLM-produced artifact must be parsed into a strict schema (JSON).
- If parsing fails, record a warning in the trace instead of crashing.
Trace everything
- Every significant step emits a JSONL trace event.
- Runs are replayable: runs/<id>/plan.json + trace.jsonl + generated workspace.
Small, boring tech
- Prefer standard library + a few well-known libs (Typer, Pydantic, PyYAML, Rich).
- Avoid "framework soup" in v0.1.

Repo layout

src/solo_company_os/cli.py
Typer CLI entrypoint (solo-company).
src/solo_company_os/core/skill.py
Parses SKILL.md (YAML frontmatter + Markdown body).
src/solo_company_os/core/skill_index.py
Discovers skills under:
- .agents/skills/
- .github/skills/
- .claude/skills/
- ~/.claude/skills/, ~/.codex/skills/
src/solo_company_os/core/orchestrator.py
Plan → execute work orders → write artifacts → RUN.md
src/solo_company_os/core/providers/
Provider abstraction:
- mock.py: deterministic, offline, used by CI
- openai_compatible.py: OpenAI-compatible /v1/chat/completions for real runs
.agents/skills/*/SKILL.md
Example skills shipped with the repo.
scenarios/
Example mission files.

Output contract conventions

For all skills in this repo, the active agent must return ONLY JSON:

Read the full file on GitHub · 93 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.

2mo ago First seen · 93 lines · 762 tokens per session scan A eab427240548

Subscribe to this mod's changes

solo-compay-os AGENTS.md is an instructions file published in the GitHub repository hubo0520/solo-compay-os (5 stars, last pushed 8mo ago), licensed MIT. It adds 762 tokens to every session, about $0.0030 per session on Opus 5.5. 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.

Building agents

solo-compay-os AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
solo-compay-os AGENTS.mdhubo0520/solo-compay-os	Instructions file	5	8mo ago	MIT	A	762	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

solo-compay-os: Instructions file for Codex