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.
npx agentmods add instructions/gerg/ai_agent_skills/agents-mdgit clone --depth 1 https://github.com/Gerg/ai_agent_skillsWrote 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.
[](https://agentmods.dev/instructions/gerg/ai_agent_skills/agents-md)<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>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 | $0.00310 | $0.00310 |
| Opus 5 | $0.00155 | $0.00155 |
| Sonnet 5 | $0.00062 | $0.00062 |
| Haiku 4.5 | $0.00031 | $0.00031 |
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.
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.
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.
- 4d ago First seen · 27 lines · 310 tokens per session scan A 3e6b265d4e19
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.
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).
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.
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.
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).
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.
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.