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.
npx skills add easyinplay/harnessed --skill karpathy-baselinegit clone --depth 1 https://github.com/easyinplay/harnessedWrote 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.
[](https://agentmods.dev/skills/easyinplay/harnessed/karpathy-baseline)<a href="https://agentmods.dev/skills/easyinplay/harnessed/karpathy-baseline"><img src="https://agentmods.dev/badge/skills/easyinplay/harnessed/karpathy-baseline/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.
<a href="https://agentmods.dev/skills/easyinplay/harnessed/karpathy-baseline"><img src="https://agentmods.dev/badge/skills/easyinplay/harnessed/karpathy-baseline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00083 | $0.00672 |
| Opus 5 | $0.00042 | $0.00336 |
| Sonnet 5 | $0.00017 | $0.00134 |
| Haiku 4.5 | $0.00008 | $0.00067 |
Grade A, and why
karpathy-baseline 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 9d 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.
What it actually says
Karpathy Baseline (心法 always-on)
ALWAYS apply these 4 心法 to every coding decision in this session. This skill is cross-cutting baseline behavior, not an opt-in tool — invoke implicitly on every implementation task, design decision, edit, and verification step.
1. Think Before Coding
先思考再写。 对新功能 / 陌生代码先 read + understand,禁止"看着改"。
- 触发:每次 implementation task。
- 反模式:直接动键盘改文件 / 不读 caller 就改 callee / 不读 schema 就动 data。
- 落地:先用 Read / Grep 拿到 ≥3 个 anchor 文件 + 1 个 caller path,再动 Edit。
2. Simplicity First (YAGNI)
最小有效代码。 不预先抽象、不预先加灵活性、不堆装配。
- 触发:每次 design decision。
- 反模式:preemptive abstraction / N×M 候选矩阵 / 多 layer of indirection。
- 落地:写最 dumb 的 working version 先,refactor 推后到第 2 caller 出现。
3. Surgical Changes
小步原子修改。 一次只改一个意图,git commit 历史保持线性可 revert。
- 触发:每次 edit。
- 反模式:mixed-concern commit / 连 refactor 带 feature / 顺手清理 unrelated code。
- 落地:每个 commit 一个 type(feat / fix / refactor / docs)+ 一个 scope + ≤200L diff。
4. Goal-Driven Execution
始终回到目标。 写代码前问"这一步要达到什么",写完问"达到了吗"。
- 触发:每个子任务起点 + 终点。
- 反模式:side quest / yak shaving / 跑偏到 unrelated refactor。
- 落地:开头复述 task goal,结尾对照 acceptance criteria 逐条 verify。
Source distilled from forrestchang/andrej-karpathy-skills (MIT). Phase 2.3 D-02 SKILL-ONLY injection (NOT CLAUDE.md sed). T0.10 fallback path: description-keyword + self-reflexive prompt discovery (SDK 0.3.142 skillFrontmatter extracts only name/source/tokens — no always_active field support).
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.
- 9d ago First seen · 51 lines · 83 tokens per session scan A a134964e8348
karpathy-baseline is a skill published in the GitHub repository easyinplay/harnessed (2 stars, last pushed 14d ago), licensed Apache-2.0. It adds 83 tokens to every session and 672 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
octowiz
Octowiz AI coding workflow coordinator. Reads IntegraHub memory doctrine at runtime, detects where you are in the development lifecycle, and routes to the right skill combination from superpowers + mattpocock-skills. Use this skill at the START of any development work — whether you have a fresh idea, an existing plan…
setup
Setup orchestrator for the Octowiz Bridge. Re-runs the live environment check, builds a gap list, and runs only the phases needed: plugins, memory, repo, verify. Invoked automatically by octowiz:octowiz when hard gaps are detected.
forge
Run a Planner→Dev→Test→Learn workflow for feature development with automatic bug-fix loops and state checkpointing.
meta-tags-optimizer
Optimize title tags, meta descriptions, Open Graph, and Twitter cards for maximum click-through rate. Generates multiple A/B test variations with character counting and SERP preview. Use when asked to "optimize title tag", "write meta description", "improve CTR", "Open Graph tags", "fix my meta tags", "social media…
google-ads-audit
Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…
sxo
Search Experience Optimization (SXO) — the bridge between SEO and UX/CRO. Audits the full journey from the SERP click to the on-page goal: SERP click-through factors (title/meta/rich results that win the click), then post-click experience signals that keep users and drive conversions — above-the-fold relevance and…