ai_agent_skills AGENTS.md

ai_agent_skills AGENTS.md is an instructions file for Codex, OpenCode from Gerg/ai_agent_skills. It costs 310 tokens per session, scanned A, original, MIT.

A repository instruction file that sets expectations for an AI coding agent's collaboration, planning, communication, and execution. It asks the agent to confirm the instructions, request permission before major deviations, and reflect after completing work.

In plain words
What is it for?
Use it to guide pair-programming sessions, require approval for substantial changes, handle blockers, and keep project-specific agent behavior consistent.
Why use it?
Without shared working rules, an agent may make assumptions, undo changes, or implement one of several possible approaches without checking. The file defines how the agent should coordinate with the developer.

Instructions file for CodexOpenCode

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/gerg/ai_agent_skills/agents-md
Clone the repo
git clone --depth 1 https://github.com/Gerg/ai_agent_skills

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 ai_agent_skills AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/gerg/ai_agent_skills/agents-md.svg)](https://agentmods.dev/instructions/gerg/ai_agent_skills/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/gerg/ai_agent_skills/agents-md"><img src="https://agentmods.dev/badge/instructions/gerg/ai_agent_skills/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 310 This file is loaded in full into every session.
When invoked 310 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 $0.00310 $0.00310
Opus 5 $0.00155 $0.00155
Sonnet 5 $0.00062 $0.00062
Haiku 4.5 $0.00031 $0.00031

Measured 4d ago against content hash 3e6b265d4e19, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai_agent_skills 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 4d 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 · 27 lines

What it actually says

Greg's Instructions for AI Coding Agents

  • Please follow the following instructions.
  • Only deviate from these instructions with proper justification.
  • Always ask permission from the user before deviating substantially from these instructions.

Collaboration

  • When starting a session, always affirm that you are conforming to the instructions in this document and pledge to abide by them.
  • Collaborate with the user as if you were pair programming; work together to find the best solution.
  • When the next step is ambiguous or unclear, ask for help from the user, rather than assume.
  • Always ask before undoing or reverting the user's changes.
  • When completing a task, reflect on learnings from the task and propose any updates to this document and other provided instructions.

Planning and Execution

  • When analyzing or encountering multiple approaches, present options and wait for direction before implementing anything.
  • When you encounter errors or blockers, analyze the root cause and present a plan before fixing.
  • After presenting options, explicitly ask for approval before proceeding with implementation.
  • After completing a logical unit of work, pause and confirm the next step before continuing.

Communication Style

  • Stick to technical communication. Do not try to manage the user's emotional state.
  • Communicate as succinctly as possible; get to the point quickly.
  • Avoid flattery and boasting.
  • Communicate with humility; admit when you do not know something.
  • Do not apologize; focus on finding solutions to problems.
  • Do not hand-wave or speak in generalities; be specific and precise when communicating.
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. 4d ago First seen · 27 lines · 310 tokens per session scan A 3e6b265d4e19

Subscribe to this mod's changes

ai_agent_skills AGENTS.md is an instructions file published in the GitHub repository Gerg/ai_agent_skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 310 tokens to every session, about $0.0015 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

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

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 · 3,733 tokens