What is LLM-Wiki-AIResearch AGENTS.md?

A repository instruction file for an LLM-maintained research wiki, a collection of linked notes about computer-science work.

Use it when working in that wiki to follow its reading order, distinguish source material from maintained pages, and update indexes and logs correctly.

It tells an AI agent what the repository contains, which files to read first, and how to make structural changes safely.

How wintersdragon-c/LLM-Wiki-AIResearch configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to wintersdragon-c/LLM-Wiki-AIResearch. 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/wintersdragon-c/LLM-Wiki-AIResearch/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/wintersdragon-c/LLM-Wiki-AIResearch

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/wintersdragon-c/llm-wiki-airesearch/agents-md/github.svg)](https://agentmods.dev/instructions/wintersdragon-c/llm-wiki-airesearch/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/wintersdragon-c/llm-wiki-airesearch/agents-md"><img src="https://agentmods.dev/badge/instructions/wintersdragon-c/llm-wiki-airesearch/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/wintersdragon-c/llm-wiki-airesearch/agents-md"><img src="https://agentmods.dev/badge/instructions/wintersdragon-c/llm-wiki-airesearch/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,586 This file is loaded in full into every session.

When invoked 1,586 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	$0.01586	$0.01586
Opus 5.5	$0.00634	$0.00634
Sonnet 5.5	$0.00317	$0.00317
Haiku 4.5	$0.00159	$0.00159

Measured 2mo ago against content hash f1f4e42432b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

LLM-Wiki-AIResearch 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 · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

What This Repository Is

This repository is an LLM-maintained research wiki for computer science work. It is a persistent markdown knowledge base, not an application codebase.

Read LLM-wiki.md for the pointer to the original Karpathy gist, then read research-map.md, index.md, and the relevant workflow document before making structural wiki edits.

Architecture

sources/ contains user-owned source folders. Read from it during ingest; do not treat it as compiled wiki output.
Root-level wiki directories (topics/, papers/, ideas/, assets/, reviews/, logs/) contain LLM-maintained markdown pages.
docs/workflows/ contains repository-owned, skill-shaped workflows. These are the authoritative procedure documents for ingest, query, maintain, and doctor operations.
AGENTS.md is the root router and hard-constraint document, not the place for full procedure bodies.

Root-level special files:

index.md — content catalog; read before every Query.
log.md — append-only global timeline; append after every content-changing operation.
research-map.md — authoritative research space map; read before every Map stage.

Required Read Order

For natural-language routing: read docs/workflows/router.md.
For source ingest: read docs/workflows/ingest.md.
For research questions over existing wiki content: read docs/workflows/query.md.
For consolidation and re-review: read docs/workflows/maintain.md.
For validation and lint-style checks: read docs/workflows/doctor.md.
Before creating or moving pages: read the target directory README.md resolver.

File Naming

All file names must be kebab-case slugs. No spaces, no uppercase, no underscores.

Directory	Pattern	Example
`topics/`	`<slug>.md`	`llm-reasoning.md`
`topics/<slug>/`	`<subtopic-slug>.md`	`chain-of-thought.md`
`papers/`	`<firstauthor>-<year>-<keyword>.md`	`wei-2022-chain-of-thought.md`
`ideas/hypothesis/`	`h-<slug>.md`	`h-process-reward-scaling.md`
`ideas/proposals/`	`p-<slug>.md`	`p-process-reward-scaling.md`
`assets/mechanisms/`	`<slug>.md`	`chain-of-thought-prompting.md`
`assets/experiment-patterns/`	`<slug>.md`	`step-level-reward-ablation.md`
`assets/evaluation-patterns/`	`<slug>.md`	`process-vs-outcome-eval.md`
`assets/failure-modes/`	`<slug>.md`	`reward-hacking-on-format.md`
`assets/negative-assets/`	`<slug>.md`	`outcome-only-supervision.md`
`reviews/`	`<slug>.md`	`process-supervision-survey.md`
`logs/`	`<YYYY-MM-DD>-<slug>.md`	`2026-04-11-ingest-audit.md`

Read the full file on GitHub · 122 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 · 122 lines · 1,586 tokens per session scan A f1f4e42432b8

Subscribe to this mod's changes

LLM-Wiki-AIResearch AGENTS.md is an instructions file published in the GitHub repository wintersdragon-c/LLM-Wiki-AIResearch (2 stars, last pushed 6mo ago), licensed MIT. It adds 1,586 tokens to every session, about $0.0063 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.

LLM-Wiki-AIResearch AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
LLM-Wiki-AIResearch AGENTS.mdwintersdragon-c/LLM-Wiki-AIResearch	Instructions file	2	6mo ago	MIT	A	1,586	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

LLM-Wiki-AIResearch: Instructions file for Codex