pm-karpathy-thinking

pm-karpathy-thinking is a skill for Claude Code, Codex from dannyhoang249-hub/pm-vietnamese-skill. It costs 62 tokens per session (753 once invoked), scanned A, original, MIT.

A product-management thinking guide for testing decisions, product requirement documents (PRDs), roadmaps, experiments, and feature ideas. It uses stated assumptions, small scopes, and measurable checks.

In plain words
What is it for?
Reviewing product plans before work starts, defining success measures, comparing alternatives, and deciding whether an experiment or feature should proceed.
Why use it?
It helps expose unclear assumptions, unnecessary scope, risks, and solution ideas that do not address the real problem. It supports clearer go/no-go decisions.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the pm-vietnamese-copilot plugin — 4 skills, 9 commands shipped together

Good fit Reviewing product plans before work starts, defining success measures, comparing alternatives, and deciding whether an experiment or feature should proceed.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dannyhoang249-hub/pm-vietnamese-skill/pm-karpathy-thinking
Install

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.

Any agent
npx skills add dannyhoang249-hub/pm-vietnamese-skill --skill pm-karpathy-thinking
Clone the repo
git clone --depth 1 https://github.com/dannyhoang249-hub/pm-vietnamese-skill

Made for: Claude Code, Codex.

Or install pm-vietnamese-copilot, the plugin that ships this one along with the rest of its 4 skills, 9 commands.

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.

agentmods badge for pm-karpathy-thinking

README.md
[![agentmods](https://agentmods.dev/badge/skills/dannyhoang249-hub/pm-vietnamese-skill/pm-karpathy-thinking/github.svg)](https://agentmods.dev/skills/dannyhoang249-hub/pm-vietnamese-skill/pm-karpathy-thinking)
Your own site
<a href="https://agentmods.dev/skills/dannyhoang249-hub/pm-vietnamese-skill/pm-karpathy-thinking"><img src="https://agentmods.dev/badge/skills/dannyhoang249-hub/pm-vietnamese-skill/pm-karpathy-thinking/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.

agentmods 80×15 button for pm-karpathy-thinking

Your own site · 80×15
<a href="https://agentmods.dev/skills/dannyhoang249-hub/pm-vietnamese-skill/pm-karpathy-thinking"><img src="https://agentmods.dev/badge/skills/dannyhoang249-hub/pm-vietnamese-skill/pm-karpathy-thinking.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 753 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00062 $0.00753
Opus 5 $0.00031 $0.00377
Sonnet 5 $0.00012 $0.00151
Haiku 4.5 $0.00006 $0.00075

Measured 12d ago against content hash 27499519cebb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

pm-karpathy-thinking 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 12d 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.

skills/pm-karpathy-thinking/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Karpathy-inspired PM Thinking | Tư duy Karpathy cho PM

Apply four behavior principles—adapted from multica-ai/andrej-karpathy-skills—to product decisions. Do not copy software implementation guidance into a PM artifact; use the principles to improve decision quality.

Language | Ngôn ngữ

Match the requester’s language. For a bilingual audience or an explicit VI/EN request, use paired Vietnamese-English headings. Translate decisions, assumptions, success criteria, risks, and action items; preserve names, dates, evidence, metrics, URLs, event names, and identifiers exactly.

Four principles | Bốn nguyên tắc

1. Think before acting | Nghĩ trước khi làm

  • State facts, assumptions, unknowns, and decision constraints separately.
  • Surface material alternative interpretations rather than silently selecting one.
  • Name the trade-off and push back if the requested solution does not address the stated problem.
  • Ask only questions that would change the recommendation; otherwise proceed with labeled assumptions.

2. Simplicity first | Đơn giản trước

  • Recommend the smallest viable scope, experiment, analysis, or release that can test the outcome now.
  • Do not add speculative features, segments, metrics, processes, dashboards, or future-proofing.
  • Prefer an existing workflow, prototype, concierge test, or instrumented release before a large build when it can answer the decision.
  • Ask: would an experienced PM call this scope overcomplicated? If yes, simplify.

3. Surgical scope | Phạm vi có chủ đích

  • Trace every proposed requirement, task, and metric to an explicit user outcome, risk, or constraint.
  • Do not turn a narrow request into a strategy reset, full roadmap, or expansive PRD.
  • Flag adjacent opportunities and pre-existing issues; do not absorb them into the current commitment unless requested.
  • Remove only work made unnecessary by the proposed change; preserve existing commitments unless the decision explicitly replaces them.

Read the full file on GitHub · 61 lines

Files

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.

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.

  1. 12d ago First seen · 61 lines · 62 tokens per session scan A 27499519cebb

Subscribe to this mod's changes

pm-karpathy-thinking is a skill published in the GitHub repository dannyhoang249-hub/pm-vietnamese-skill (1 stars, last pushed 24d ago), licensed MIT. It adds 62 tokens to every session and 753 once invoked, about $0.0003 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.