karpathy-guidelines is agent-read markdown (skill) from cowork-os/cowork-os: Surgical execution guardrails for coding, debugging, review, and refactor tasks.
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Surgical Task Guidelines
## Purpose
Keep execution scoped, simple, and verifiable for coding, debugging, review, refactor, and file-editing tasks.
## Routing
- Use when: Use for coding, debugging, review, refactor, build, test, release, or file-editing tasks where scope control and verification matter.
- Do not use when: Do not use for pure brainstorming, broad strategy, or requests where the user explicitly asks for expansive ideation rather than execution.
- Outputs: A focused task result with assumptions, scoped changes, verification evidence, and unrelated issues kept separate.
- Success criteria: The result satisfies the user's request with minimal relevant changes, no drive-by edits, and clear verification evidence.
## Trigger Examples
### Positive
- Use the karpathy-guidelines skill for this request.
- Fix this bug without refactoring unrelated modules.
- Review this patch and point out overcomplicated or unnecessary changes.
- Refactor this file surgically while preserving behavior.
- Implement this feature and verify the narrowest relevant test passes.
### Negative
- Brainstorm ten moonshot product directions.
…
Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
A 17 of 17 checks passed. Deterministic, no model, same answer every run.
pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (1689 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag
Source
GitHub
cowork-os/cowork-os · 459 stars · license MIT · pushed 2026-09-23 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_5hu33mrtf43ozlbu
GET https://markdownregistry.com/api/v1/resolve?ref=cowork-os/cowork-os/karpathy-guidelines
GET https://markdownregistry.com/api/v1/blob/566dddd20c6e974b7a234ce392270c5b4c6af6d697bd640110b93608707d6e81
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
cowork-os/cowork-os · resources/plugin-packs/codex-security/skills/attack-path-analysis/SKILL.md · Use when Codex is already in the attack-path-analysis phase of a security scan or the user explicitly asks to trace a…
cowork-os/cowork-os · resources/plugin-packs/codex-security/skills/deep-security-scan/SKILL.md · Use when the user asks for a deep, exhaustive, multi-pass, or variance-reducing repository-wide Codex Security scan…
cowork-os/cowork-os · resources/plugin-packs/codex-security/skills/finding-discovery/SKILL.md · Use when Codex is already in the finding-discovery phase of a security scan or the user explicitly asks to discover…
cowork-os/cowork-os · resources/plugin-packs/codex-security/skills/fix-finding/SKILL.md · Use when the user explicitly asks to fix and verify a validated or plausible security finding. Do not use as the…
cowork-os/cowork-os · resources/plugin-packs/codex-security/skills/security-diff-scan/SKILL.md · Use when the user asks for a security review of a pull request, commit, branch diff, working-tree patch, or other…
cowork-os/cowork-os · resources/plugin-packs/codex-security/skills/security-scan/SKILL.md · Use when the user asks for a repository-wide or scoped-path security scan.
cowork-os/cowork-os · resources/plugin-packs/codex-security/skills/threat-model/SKILL.md · Use when Codex is already in the threat-modeling phase of a security scan, the user explicitly invokes $threat-model…
cowork-os/cowork-os · resources/plugin-packs/codex-security/skills/validation/SKILL.md · Use when Codex is already in the validation phase of a security scan or the user explicitly asks to determine whether…
cowork-os/cowork-os · resources/skills/1password/SKILL.md · Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or…
mxyhi/ok-skills · karpathy-guidelines/SKILL.md · Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid…
coco-research/coco · skills/karpathy-guidelines/SKILL.md · Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid…
openyida/openyida · .agents/skills/karpathy-guidelines/SKILL.md · Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid…
youdotcom-oss/agent-skills · .agents/skills/karpathy-guidelines/SKILL.md · Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid…
jjmartres/ai-coding-agents · shared/.ai-agents/skills/karpathy-guidelines/SKILL.md · Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid…
cmc-27/pass-the-parcel · .devops/skills/karpathy-guidelines/SKILL.md · Make sure to use this skill whenever you write, review, or refactor code, or when the user asks to implement a feature…
