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 VKirill/claude-lane-stack --skill karpathy-guidelinesgit clone --depth 1 https://github.com/VKirill/claude-lane-stackWrote 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/vkirill/claude-lane-stack/karpathy-guidelines)<a href="https://agentmods.dev/skills/vkirill/claude-lane-stack/karpathy-guidelines"><img src="https://agentmods.dev/badge/skills/vkirill/claude-lane-stack/karpathy-guidelines/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/vkirill/claude-lane-stack/karpathy-guidelines"><img src="https://agentmods.dev/badge/skills/vkirill/claude-lane-stack/karpathy-guidelines.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 53 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 54 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00039 | $0.00427 |
| Opus 5 | $0.00019 | $0.00214 |
| Sonnet 5 | $0.00008 | $0.00085 |
| Haiku 4.5 | $0.00004 | $0.00043 |
Grade A, and why
karpathy-guidelines 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 Guidelines
Derived from Karpathy on LLM coding pitfalls. Bias: caution over reckless speed. Trivial tasks — use judgment.
1. Think Before Coding
Don't assume. Don't hide confusion. Surface tradeoffs.
- State assumptions explicitly. If uncertain, ask.
- Multiple interpretations → present them; don't pick silently.
- Prefer simpler approaches; push back when warranted.
- Unclear → stop, name the confusion, ask.
2. Simplicity First
Minimum code that solves the problem. Nothing speculative.
- No features beyond the ask.
- No single-use abstractions or fake "flexibility".
- No error handling for impossible cases.
- 200 lines that could be 50 → rewrite.
3. Surgical Changes
Touch only what you must. Clean up only your own mess.
- Don't "improve" adjacent code, comments, or formatting.
- Don't refactor what isn't broken.
- Match existing style.
- Unrelated dead code → mention, don't delete.
- Remove only what your change made unused.
Test: every changed line traces to the user request.
4. Goal-Driven Execution
Define success criteria. Loop until verified.
- "Add validation" → tests for invalid inputs, then make them pass.
- "Fix the bug" → failing test first, then green.
- Multi-step:
step → verify: commandlist.
Strong criteria → autonomous loop. Weak ("make it work") → clarify first.
Autonomy zone (MAY)
Inside the task scope, decide tech details, edit order, and local design without asking.
Do not ask the user what you can look up in the repo or docs.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 55 lines · 39 tokens per session scan A 118fb4f69a0b
karpathy-guidelines is a skill published in the GitHub repository VKirill/claude-lane-stack (115 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 427 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
afc:learner
Review and promote learned patterns to project rules.
afc:pr-comment
Post structured review comments to GitHub PR.
afc:architect
Architecture analysis and design review.
afc:resolve
Address LLM bot review comments on PR — fix valid issues, dismiss false positives.
afc:review
Code review — review code, analyze PR diff, evaluate quality and correctness.
swarm-pr-review
Run a graph-guided, tool-augmented PR review using context packing, parallel exploration, mandatory repository-agnostic risk-family coverage with dispatch scaled to diff size and risk, independent reviewer validation, critic challenge, and metrics writeback. Use for deep pull request review with low false-positive…