ai-research-skill AGENTS.md

ai-research-skill AGENTS.md is an instructions file for Codex, OpenCode from Toadoum/ai-research-skill. It costs 224 tokens per session, scanned A, original, MIT.

A repository guide for an AI research skill, with SKILL.md as its main source of instructions. It requires research agents to read past lessons before starting and record new mistakes when they occur.

In plain words
What is it for?
It guides agents through AI and machine-learning research tasks, including preparation, following the skill instructions, and logging corrections.
Why use it?
It gives research tasks consistent rules and preserves lessons from earlier errors, reducing repeated mistakes across sessions.

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/toadoum/ai-research-skill/agents-md
Clone the repo
git clone --depth 1 https://github.com/Toadoum/ai-research-skill

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-research-skill AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/toadoum/ai-research-skill/agents-md.svg)](https://agentmods.dev/instructions/toadoum/ai-research-skill/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/toadoum/ai-research-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/toadoum/ai-research-skill/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 224 This file is loaded in full into every session.
When invoked 224 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 $0.00224 $0.00224
Opus 5 $0.00112 $0.00112
Sonnet 5 $0.00045 $0.00045
Haiku 4.5 $0.00022 $0.00022

Measured 4d ago against content hash 5b2dfdc0b004, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai-research-skill 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 · 20 lines

What it actually says

AGENTS.md

This repository is an AI research skill. The source of truth is SKILL.md.

If you are an agent that reads AGENTS.md (e.g. Codex, or OpenClaw's injected prompt path):

  1. Before any AI/ML research task, read SKILL.md and follow it.
  2. First action of every research task: read LESSONS.md — the accumulated record of past mistakes and the rules that came from them. Don't repeat them.
  3. Whenever you make and fix a mistake during the task, append a lesson via python scripts/log_lesson.py (see the self-improvement section of SKILL.md). This is what makes the skill improve over time.

Keep SKILL.md as the single place you edit behavior. This file is only a pointer so that AGENTS.md-based agents land in the same place Claude and OpenClaw skill-loaders do.

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 · 20 lines · 224 tokens per session scan A 5b2dfdc0b004

Subscribe to this mod's changes

ai-research-skill AGENTS.md is an instructions file published in the GitHub repository Toadoum/ai-research-skill (11 stars, last pushed 2mo ago), licensed MIT. It adds 224 tokens to every session, about $0.0011 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 2026-08-30.

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

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 · 4,345 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

next.js 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