using-karpathy-wiki

REVIEW · 68
Registry indexed

Auto-loaded by the SessionStart hook. Defines when to capture and routes the main agent or detached ingester to the appropriate on-demand skill.

Verified installs0
Stars101
Version1.0.0
Quality66/100 · Promising
Trust68/100 · Sandbox only
Audit79/100 · Needs review

Supply asset profile

Research and knowledge work

Deep research, source comparison, literature review, RAG, knowledge search, and reports.

Browse track

Scenario

Research agents

I need my agent to research a topic, compare sources, and produce a concise report.

Agent fit

Claude Code + OpenAI Agents + CLI

Codex, Claude Code, Cursor, CLI, or custom agents.

Install

Ready

npx skills add toolboxmd/karpathy-wiki --skill using-karpathy-wiki

Maintenance

fresh

2d since push

Risk

Needs review

Permission surface may require sandboxing

GitHub quality

101

66/100 Quality · 76/100 Trust

Coverage tags

ResearchResearch agentsautomationagent-skill

Review notes

Permission surface may require sandboxing · Financial research output is not financial advice; require human review before any live investment decision

Agent adoption scorecard

Trust, audit, and install readiness at a glance

These scores combine public repository metadata, OpenAgentSkill review signals, maintenance freshness, and install readiness. They are a shortlist signal, not a replacement for human review.

Quality

Promising
66

Useful candidate, but compare it with alternatives before adopting.

Trust

Sandbox only
68

Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.

Audit

Needs review
79

A machine-readable review of install readiness, security metadata, maintenance, and adoption risk.

OpenAgentSkill Trust Score v5

Human review before install

Run only in a sandbox and compare close alternatives before using it for real work.

CodexClaude CodeCursorOpenAgentSkill CLI

Stars

101 GitHub stars

Repo activity

101 stars, 24 forks

Maintenance

2d since push

License

MIT

Install

npx skills add toolboxmd/karpathy-wiki --skill using-karpathy-wiki

Install safety

standard package or runtime install path

Permission surface

shell or command execution, filesystem or document access

Agent outcomes

No agent outcome data yet

Docs

Strong README/SKILL.md context

Risk summary

Review before production

  • Financial research output is not financial advice; require human review before any live investment decision.
  • Quality score needs review
  • Permission surface needs review: shell or command execution, filesystem or document access
  • Stars/forks activity: 101 stars, 24 forks; issue activity unavailable in current metadata

Install readiness

Install path available

  • Install path is available
  • Repository evidence is available
  • License is declared
  • No Agent Proven outcome evidence yet

Agent-readable metadata

Machine-readable decision data for this skill.

Use this block or the embedded JSON to decide whether an agent should install this skill, choose an alternative, or ask for human review first.

Open JSON

Suited tasks

  • Research agents workflows
  • Claude Code teams
  • builders willing to evaluate younger projects
  • Search sources

Suited agents

CodexClaude CodeCursorOpenAgentSkill CLIOpenAI AgentsCLI

Install decision

Command
npx skills add toolboxmd/karpathy-wiki --skill using-karpathy-wiki
Policy
review
Human review
yes

Trust and risk

Trust
68/100
Audit
79/100
Risk level
Needs review

Outcome loop

Endpoint
/api/agent/outcome
Event ID
resolve
Outcomes
5

Install command

npx skills add toolboxmd/karpathy-wiki --skill using-karpathy-wiki

Do not use when

  • teams that need a vendor-supported SLA
  • high-compliance environments without internal security review
  • No major risk signals from current metadata
  • High-risk permission hints: Shell or command execution
  • Permission surface may require sandboxing

Agent safety v2

47/100 · Avoid automatic install

Experimentalreview

Sparse or mixed signals. Useful for discovery, but not for autonomous installation.

Test manually in an isolated workspace and compare against safer alternatives.

Resolve via API

high

Shell or command execution

Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.

medium

Network access

Skill likely fetches remote pages, APIs, repositories, or external services.

medium

Filesystem access

Skill may read or write project files, documents, generated artifacts, or local workspace state.

medium

Database access

Skill may inspect schemas, query databases, or work with persistent stores.

  • High-risk permission hints: Shell or command execution
  • Permission surface may require sandboxing

Install targets

Install this skill in your agent workflow

Use the public install endpoint to fetch the command, safety checklist, target prompts, and canonical links for this skill.

skill install

OpenAgentSkill CLI

Resolve policy, run the source installer safely, and report a verified install receipt.

$ npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install toolboxmd-using-karpathy-wiki

Agent resolve plan

Let an agent verify fit before installing.

The Resolve API returns the selected skill, alternatives, safety policy, audit notes, install target, and copy-paste prompt an agent can follow without scraping this page.

Open text plan

Agent should check

  • Task fit and alternatives from Resolve API.
  • Audit score, trust score, and safety policy warnings.
  • Install target compatibility for Codex, Claude Code, Cursor, or CLI.

Copy prompt

Task: Use using-karpathy-wiki in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20using-karpathy-wiki%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/toolboxmd-using-karpathy-wiki/install
Install command: npx skills add toolboxmd/karpathy-wiki --skill using-karpathy-wiki
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.

Agent handoff

Give an agent the install path, not another directory page.

Use the public install endpoint to fetch the command, safety checklist, target prompts, and canonical links for this skill.

Open install API

Agent prompt

Use using-karpathy-wiki for this task. Review https://www.openagentskill.com/api/skills/toolboxmd-using-karpathy-wiki/install, then install with: npx skills add toolboxmd/karpathy-wiki --skill using-karpathy-wiki

Registry metadata

Agent-readable profile for automatic skill selection.

This page exposes the same decision, trust, audit, use-case, and install signals through the Registry API, so agents can rank this skill without scraping the UI.

Open manifest

Agent fit

68/100

Research agents

Platforms

Claude Code, OpenAI Agents

Audit report

Needs review · 79/100

A machine-readable review of install readiness, security metadata, maintenance, and adoption risk.

View audit reportView eval report

Agent decision cockpit

Fallback candidate for Research agents

Prototype with this skill first; keep a fallback candidate ready.

68
Readiness
Prototype
Stage

Role in stack

Fallback candidate

Primary fit

Research agents

Trust label

Prototype first

Install path

Command ready

Use when

  • Research agents workflows
  • Claude Code teams
  • builders willing to evaluate younger projects

Evidence

  • recent repository activity
  • install command or GitHub repo available
  • 66/100 quality profile
  • 7 OpenAgentSkill engagement events

review first

  • No major risk signals from current metadata

Implementation path

  1. 1Install it in a sandbox agent and run one Research agents task end to end.
  2. 2Compare output quality, latency, and failure behavior against at least one alternative.
  3. 3Promote it into production only after reviewing repository permissions, license, and maintenance signals.

Trust profile

Sandbox only

Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.

68
OpenAgentSkill Trust Score

GitHub adoption

INFO

101 GitHub stars

Stars/forks activity

CHECK

101 stars, 24 forks; issue activity unavailable in current metadata

Recent maintenance

PASS

2d since push

License clarity

PASS

MIT

Good signals

  • AI review approved
  • Install path is available
  • Repository evidence is available
  • Recently maintained repository
  • Install command has no obvious high-risk pattern
  • Outcome loop is ready but needs first real agent run

Review before install

  • Financial research output is not financial advice; require human review before any live investment decision.
  • Quality score needs review
  • Permission surface needs review: shell or command execution, filesystem or document access
  • Stars/forks activity: 101 stars, 24 forks; issue activity unavailable in current metadata
  • Permission surface: shell or command execution, filesystem or document access
  • No real agent outcome reports yet
  • Human review required before unattended installation

Recommended action

Run only in a sandbox and compare close alternatives before using it for real work.

Quality profile

Promising candidate for agent workflows

Useful candidate, but compare it with alternatives before adopting.

66
GitHub stars
101
Freshness
2d ago
Install ready
Yes
License
MIT

Workflow fit

Use this skill in these scenarios

Workflow fit

Add it to a complete workflow

Alternative shortlist

Compare before you install

Similar skills that may fit this task.

Compare all

Overview

--- name: using-karpathy-wiki description: | Auto-loaded by the SessionStart hook. Defines when to capture and routes the main agent or detached ingester to the appropriate on-demand skill. ---

<SUBAGENT-STOP> If you were dispatched as a subagent for a task unrelated to wiki capture or ingest, skip this skill. The wiki rules apply to the main agent in the conversation; subagents doing isolated work (Explore, code-reviewer, codex:rescue, etc.) do not need to capture. </SUBAGENT-STOP>

# karpathy-wiki — loader (read once per session, applies for the whole session)

You are operating in a project that uses the karpathy-wiki plugin. Durable knowledge surfaced in this conversation must be captured to a wiki so future sessions can find it.

## Announce when you act

When you write a capture, run an ingest, or answer from the wiki, prefix your reply with one line:

> **Using the karpathy-wiki skill to [capture this / ingest pending captures / answer from wiki].**

This is the ONLY wiki-mechanics text the user sees. Do not narrate orientation, capture authoring, dispatch mechanics, or state-machine progress. Do all the wiki work silently after the announce line.

## Instruction priority

If the user's `CLAUDE.md` / `AGENTS.md` or an explicit user instruction conflicts with the rules below, follow the user. The wiki rules override the default system prompt where they conflict, but **never** override the user's direct instructions.

## Iron laws

``` NO WIKI WRITE IN THE FOREGROUND NO PAGE EDIT WITHOUT READING THE PAGE FIRST NO SKIPPING A CAPTURE BECAUSE "IT DOESN'T LOOK WIKI-SHAPED" NO ANSWERING ANY USER QUESTION WITHOUT ORIENTING FIRST ```

Captures go to `<wiki>/.wiki-pending/<timestamp>-<slug>.md`. The bounded dispatcher assigns each capture to the configured provider/model profile and ingests it in the background.

## Orient before answering — the read protocol

For ANY user message that is asking a QUESTION (vs requesting a code edit, file operation, or pure command), you must orient on the wiki BEFORE drafting the answer. Pre-classifying a question as "general knowledge" or "not wiki-relevant" is the forbidden rationalization Iron Rule 4 was written to forbid.

**Cost framing.** Orientation is a once-per-session investment:

- First wiki-eligible question of the session: read `<wiki>/schema.md` and the relevant `<wiki>/<category>/_index.md` (or root `<wiki>/index.md` for cross-category questions). Two file reads, ~10-30 KB total. - Subsequent questions in the same session: the schema and index are already in your working memory; the marginal check is a candidate-count scan against the (already-read) `_index.md`. Near-zero cost.

Load `karpathy-wiki-read/SKILL.md` for the deterministic 6-step ladder (orient → count candidates → inline-read OR subagent OR web-search → cite). Do NOT skip the load because "this question seems trivial" — the iron rule is unconditional.

**Resist-table for the read protocol** (capture-side resist-table is below, after TRIGGER):

| Rationalization | Reality | |---|---| | "This is general knowledge / I know this from training" | Pre-classifying questions as wiki-irrelevant is the forbidden rationalization. The wiki's scope is whatever has been captured. You don't know without checking. Orient. | | "This question is trivial; reading two files is overkill" | Orientation is once per session. After the first orient, the marginal cost on the next question is near-zero (a re-scan of the already-read `_index.md`). The "trivial question" carve-out is the same drift that dropped the read protocol in v2.4. | | "Pure syntax question, the wiki won't cover this" | You cannot know without checking. If `_index.md` has zero matches, the read skill's Step F handles it (web search + capture the gap). The orient itself is what proves there are no candidates. | | "User asked me to fix a bug, not answer a question" | Code-edit requests don't trigger the read protocol; question-shaped requests do. If unsure (e.g. "why isn't this working" — could be a question OR a debug request), orient. | | "I already oriented earlier this session, I'll skip this time" | Correct! Re-use the schema and index you already have. Run only the candidate-count check on the new question's terms. The protocol's deterministic part (Step B) is the only thing that re-runs per question. |

## TRIGGER — when to capture

Write a capture when ANY of these fire (immediate-capture triggers):

- A research subagent or research agent completes or returns a file with durable findings. - New factual information is found (web search, doc fetch, external fact surfaced in conversation). - Session resolves a confusion — something neither of you knew before. - A gotcha, quirk, or non-obvious behavior in a tool is discovered. - A pattern is validated (approaches compared, one picked, with reasons). - An architectural decision is made with explicit rationale. - User pastes a URL or document for study. - `<wiki>/inbox/` or `<wiki>/raw/` has unprocessed files. - User says "add to wiki" / "remember this" / "wiki it" / "save this". - Two claims contradict each other.

Also TRIGGER (orientation + citation): the user asks "what do we know about X" / "how do we handle Y" / "what did we decide about Z" / "have we seen this before" — or any question the wiki might cover.

## SKIP — when not to capture

- Routine file edits, syntax lookups, one-off debugging with trivial root causes. - Time-sensitive data that must be fetched fresh. - Questions clearly outside any wiki's scope.

Do NOT skip based on tone or shape. "This looks like casual chat", "there's no code here", "this isn't a wiki context" are forbidden rationalizations. If new factual information appeared, capture. Tone is not the trigger.

**Resist-table for capture triggers.** When you're about to skip a capture, check these red flags. Skipped captures are invisible — the user cannot observe them, so the discipline is yours alone.

| Rationalization | Reality | |---|---| | "The user will remember this" | The user will not remember. That's the whole point. | | "It's too trivial for the wiki" | If a TRIGGER fires, capture. Lint and the ingester filter noise later. | | "I'll capture it later" | Later means never. Capture now — invocation is milliseconds. | | "I'm in the middle of another task" | Capture is non-blocking; `bin/wiki capture` writes a file and returns. The ingester runs detached. | | "The user didn't ask me to save this" | Triggers fire automatically. No explicit user request is required — that's the loader's contract. | | "I don't have a memory tool available" | This skill IS the memory tool. The loader's presence is the trigger. | | "The file is already in a good place" | Filing ≠ capturing. Location is not organization. The capture extracts the durable concept from the file's context; the file alone doesn't. |

## What to do when a trigger fires

For chat-driven captures (the conversation IS the source, or you have a file alongside the conversation): load `karpathy-wiki-capture/SKILL.md` and follow it. The capture is written via `bin/wiki capture` (a subcommand of the existing `bin/wiki` CLI).

For research subagent reports (a file is the source): the agent's job is one command, NOT a hand-written capture body:

```bash mv <subagent-report-path> <wiki>/inbox/<basename> wiki ingest-now <wiki> # or wait for next SessionStart ```

For ANY user question (including "what does the wiki know about X" questions, but also any other question per Iron Rule 4): load `karpathy-wiki-read/SKILL.md` and run the deterministic 6-step ladder. Do NOT load `karpathy-wiki-ingest/SKILL.md` — that's for the detached runtime ingester only and contains write-side machinery the main agent never needs.

## Mode change

If the user asks to change the wiki mode for this directory (phrases like "use project wiki here," "main only," "switch to both," "fork to main"), run:

```bash wiki use project|main|both ```

Confirm the change in one line; do not over-narrate.

## What's NOT in this loader

The full operational details — capture format, body-size floors, dispatch mechanics, ingester orientation, page format, manifest protocol, commit conventions — live in the on-demand skills:

- `skills/karpathy-wiki-capture/SKILL.md` — load when you are about to write a capture. - `skills/karpathy-wiki-read/SKILL.md` — load when you are about to answer a user question (Iron Rule 4). - `skills/karpathy-wiki-ingest/SKILL.md` — loaded by the detached ingester via its provider prompt; the main agent never reads this.

If you do not know what to do at a particular step, load the on-demand skill — do not invent.

Technical details

Version
1.0.0
License
MIT
Last updated
Aug 20, 2026
Published
Aug 20, 2026

Decision snapshot

Fallback candidate

68
Ready
Prototype
Stage

recent repository activity

Audit

Install review

Install and adoption review

79
Needs review
Security
79/100
Maintenance
100/100
Install
92/100
Open full auditView eval report

Agent-proven evidence

Agent-proven evidence

Outcome reports after resolve, review, install, and one narrow run.

0
Proven
Needs first agent runAuto-install: review firstLast: Unknown
Success rate
Recent failure
Outcomes
0
Output quality
Failed
0
Not relevant
0
Installs
0
Risk blocked
0
Setup needed
0
Production
0

No agent outcome data yet. The first agent run can report success, setup needs, risk blocks, failure, or not-relevant through /api/agent/outcome.

Install

Add to agent workflow

Free and open source. Review the report before installing into production agents.

Growth loop

Share kit

X

Scenario-led draft for using-karpathy-wiki, ready for a manual X post.

Curator note
using-karpathy-wiki: Auto-loaded by the SessionStart hook. Defines when to capture and routes the main agent or de...

101 stars

https://www.openagentskill.com/skills/toolboxmd-using-karpathy-wiki?ref=x
Open X draft
Optional reply with install command
Listing + install path for using-karpathy-wiki:
https://www.openagentskill.com/skills/toolboxmd-using-karpathy-wiki?ref=x

Install: npx skills add toolboxmd/karpathy-wiki --skill using-karpathy-wiki

Listing source

Registry indexed

Claimable

This listing was indexed from public sources and is not marked official until a maintainer claim is approved.

Creator
toolboxmd
Indexed by
OpenAgentSkill community index

Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals.

Claim this skill

Owner claim

Claim this skill listing

This Registry indexed listing is attributed to toolboxmd but is not marked official yet. Claim it to add a verified owner signal and make future launch, install, and audit updates easier to trust.

Creator backlink kit

Add the evidence badges to your README

Show the canonical listing, current trust and audit signals, and real Agent-Proven evidence where developers evaluate the repository.

[![Listed on OpenAgentSkill](https://www.openagentskill.com/api/badge/toolboxmd-using-karpathy-wiki?metric=listed&label=Listed)](https://www.openagentskill.com/skills/toolboxmd-using-karpathy-wiki)
[![OpenAgentSkill Trust](https://www.openagentskill.com/api/badge/toolboxmd-using-karpathy-wiki?metric=trust&label=Trust)](https://www.openagentskill.com/skills/toolboxmd-using-karpathy-wiki)
[![OpenAgentSkill Audit](https://www.openagentskill.com/api/badge/toolboxmd-using-karpathy-wiki?metric=audit&label=Audit)](https://www.openagentskill.com/skills/toolboxmd-using-karpathy-wiki/audit)
[![Agent Proven](https://www.openagentskill.com/api/badge/toolboxmd-using-karpathy-wiki?metric=proven&label=Agent%20Proven)](https://www.openagentskill.com/skills/toolboxmd-using-karpathy-wiki)

Author

T

toolboxmd

@toolboxmd

Health signals

GitHub stars
101
Quality score
37/100
Last GitHub push
Aug 20, 2026
Framework hints
Unknown
OpenAgentSkill views
7
Install copies
0
Outbound clicks
0

Community signal

Share whether this skill looks useful for your agent workflow. Aggregated feedback improves rankings over time.

Trust & safety

Sandbox only

68
  • GitHub adoption101 GitHub starsINFO
  • Stars/forks activity101 stars, 24 forks; issue activity unavailable in current metadataCHECK
  • Recent maintenance2d since pushPASS
  • License clarityMITPASS
  • README/SKILL.md completenessMetadata includes enough usage and workflow contextPASS
  • Dependency/runtime riskcommand execution surface, network or browser surfaceINFO