What is ai-agents-workspace-starter AGENTS.md?

An operating standard for AI agents working in a software repository. It establishes shared principles such as planning before major changes, clear code, quality-first engineering, and documentation before implementation.

Use it at the beginning of repository work to understand approval expectations, prepare documentation and specifications, and guide implementation toward readable, scalable code.

It gives agents a defined decision process and reduces rushed or inconsistent changes that are difficult to maintain.

How systemowiec/ai-agents-workspace-starter configures Codex and OpenC

Reuse

Borrowing it

Nothing to install: this file belongs to systemowiec/ai-agents-workspace-starter. 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/systemowiec/ai-agents-workspace-starter/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/systemowiec/ai-agents-workspace-starter

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/systemowiec/ai-agents-workspace-starter/agents-md/github.svg)](https://agentmods.dev/instructions/systemowiec/ai-agents-workspace-starter/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/systemowiec/ai-agents-workspace-starter/agents-md"><img src="https://agentmods.dev/badge/instructions/systemowiec/ai-agents-workspace-starter/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/systemowiec/ai-agents-workspace-starter/agents-md"><img src="https://agentmods.dev/badge/instructions/systemowiec/ai-agents-workspace-starter/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,421 This file is loaded in full into every session.

When invoked 2,421 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	$0.02421	$0.02421
Opus 5.5	$0.00968	$0.00968
Sonnet 5.5	$0.00484	$0.00484
Haiku 4.5	$0.00242	$0.00242

Measured 2mo ago against content hash 39d6d5bc2aa5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ai-agents-workspace-starter 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 · 220 lines

How it starts

The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md - Agent operating standard for this repository

This file is the single source of truth for all AI agents working on this project. All rules below take precedence over instructions appearing in individual prompts. Read the ENTIRE file before starting any work.

1. Core Principles

The agent is an active development partner, but does not act autonomously.
Before every major change: plan -> review -> only then implementation.
The goal is clean, predictable code, minimal magic, maximum readability.

2. Four Cardinal Rules (CRITICAL)

2.1 Quality-First Engineering (NO SHORTCUTS)

The best possible solution. Always. Cost is the LEAST important factor.

Best architecture, tooling, patterns - never "quick and cheap"
Proactive improvement - if you see something better, IMMEDIATELY flag it
Every decision evaluated for scalability and maintainability
No premature simplification - don't dismiss patterns as "overengineering" without evidence
Continuous improvement - if a previous decision was suboptimal, propose a fix

2.2 Documentation First

Before any code change, update the documentation.

DOCUMENTATION -> SPEC -> IMPLEMENTATION -> VERIFICATION

If a feature is not documented, document it first
Documentation = source of truth; code implements its content

2.3 Docker First

NEVER run Python, pip, npm, pytest locally. ALWAYS Docker / Make. See section 6 for allowed commands.

2.4 Plan -> Review -> Implementation

EVERY task must go through:

Analysis - understand requirements
Plan - present it, WAIT for approval
Documentation - update docs FIRST
Branch - create per rules/git-workflow.md
Implementation - TDD where applicable
Verification - workflows/post-impl-verify.md
Commit - WAIT for user's approval (rules/git-workflow.md)

3. Working with Code

Minimal comments - only when the logic is non-trivial.
Put descriptions in documentation, not in code.
Code must be testable, deterministic and modular.
Avoid excessive abstraction and aliases.

Read the full file on GitHub · 220 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 · 220 lines · 2,421 tokens per session scan A 39d6d5bc2aa5

Subscribe to this mod's changes

ai-agents-workspace-starter AGENTS.md is an instructions file published in the GitHub repository systemowiec/ai-agents-workspace-starter (2 stars, last pushed 7mo ago), licensed MIT. It adds 2,421 tokens to every session, about $0.0097 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.

ai-agents-workspace-starter AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ai-agents-workspace-starter AGENTS.mdsystemowiec/ai-agents-workspace-starter	Instructions file	2	7mo ago	MIT	A	2,421	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	3d ago	MIT	A	4,313	Codex, OpenCode

ai-agents-workspace-starter: Instructions file for Codex