What is karpathy-wiki AGENTS.md?

Project instructions for contributing to karpathy-wiki, including planning handoffs, project tracking files, and recent changes. A project ledger is a set of files that records work, known problems, and ideas.

Use it when modifying karpathy-wiki, especially around test policy, planning documents, ledger files, ingestion, or wiki maintenance.

It prevents contributors and agents from changing tests or project records without following the repository's current process.

How toolboxmd/karpathy-wiki configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to toolboxmd/karpathy-wiki. 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/toolboxmd/karpathy-wiki/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/toolboxmd/karpathy-wiki

Made for: Claude Code, 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/toolboxmd/karpathy-wiki/agents-md/github.svg)](https://agentmods.dev/instructions/toolboxmd/karpathy-wiki/agents-md)

Your own site

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

Per session 919 This file is loaded in full into every session.

When invoked 919 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	$0.00919	$0.00919
Opus 5.5	$0.00368	$0.00368
Sonnet 5.5	$0.00184	$0.00184
Haiku 4.5	$0.00092	$0.00092

Measured 2mo ago against content hash eb3338eb001d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

karpathy-wiki 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 · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Contributing to karpathy-wiki

Active planning handoff

Before changing test policy or removing, merging, or demoting tests, read docs/planning/2026-08-12-test-strategy-rightsizing-handoff.md. The first phase is a read-only portfolio audit and must stop for human review. Remove this pointer when that workstream is resolved.

Project ledger files

Use the global project-ledger convention when adding or pruning local CHANGELOG.md, TODO.md, ISSUES.md, and IDEAS.md.

In this repository, ISSUES.md means a local known-problems scratchpad. It is not the wiki issues command, not .ingest-issues.jsonl, not a GitHub Issues replacement, and not a work-package manifest.

Recent Changes

2026-08-27: Schema-proposals retired. Ingest logs schema-drift; doctor archives leftover files. Init no longer creates that inbox.
2026-08-27: karpathy-wiki is a three-host plugin in marketplace toolboxmd (Codex, Claude Code, Grok Build). It is not the marketplace.
2026-08-27: Ingest must-augment clustered objects, silently patches schema.md, and a detached wiki doctor census runs on schema cadence (Grok xhigh, Codex max fallback). Doctor does not rewrite page bodies.
2026-08-26: Read Step B uses per-index document frequency: rare terms select, common terms (6+ hits, including tags on the index line) AND-filter unless that would empty the set. Related-only ingest does not append sources:.
2026-08-21: Split the old combined backlog into CHANGELOG.md, TODO.md, ISSUES.md, and IDEAS.md.

If you are an AI agent

Before opening a PR against this repo:

Read the PR template (when one exists) and answer every prompt; do not skip prompts you find redundant.
Search for existing PRs on the same topic. Duplicates get closed.
Verify a real problem exists. Cite the failing test, the wrong output, or the user-reported bug. Do NOT fabricate problem descriptions.
Show your human partner the complete diff before submitting. Walk them through it.

Read the full file on GitHub · 81 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 · 81 lines · 919 tokens per session scan A eb3338eb001d

Subscribe to this mod's changes

karpathy-wiki AGENTS.md is an instructions file published in the GitHub repository toolboxmd/karpathy-wiki (105 stars, last pushed 19d ago), licensed MIT. It adds 919 tokens to every session, about $0.0037 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 2026-08-30.

Planning

karpathy-wiki AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
karpathy-wiki AGENTS.mdtoolboxmd/karpathy-wiki	Instructions file	105	19d ago	MIT	A	919	Claude Code, 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	today	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

karpathy-wiki: Instructions file for Claude Code