strategy-kernel

strategy-kernel is a skill for Claude Code, Codex from exiao/pm-skills. It costs 129 tokens per session (1,932 once invoked), scanned A, original, Apache-2.0.

A guide for creating or reviewing a strategy using Richard Rumelt’s three-part method: diagnosis, guiding policy, and coordinated actions.

In plain words
What is it for?
Use it to pressure-test a proposed strategy or write one that clearly identifies the challenge, the chosen approach, and the actions that support it.
Why use it?
It separates a practical response to a real obstacle from vague goals, slogans, or lists of unrelated projects.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/exiao/pm-skills/strategy-kernel
Any agent
npx skills add exiao/pm-skills --skill strategy-kernel
Clone the repo
git clone --depth 1 https://github.com/exiao/pm-skills

Made for: Claude Code, Codex.

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 strategy-kernel

README.md
[![agentmods](https://agentmods.dev/badge/skills/exiao/pm-skills/strategy-kernel.svg)](https://agentmods.dev/skills/exiao/pm-skills/strategy-kernel)
Your own site
<a href="https://agentmods.dev/skills/exiao/pm-skills/strategy-kernel"><img src="https://agentmods.dev/badge/skills/exiao/pm-skills/strategy-kernel.svg" alt="Measured on agentmods" height="20"></a>
Per session 129 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,932 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00129 $0.01932
Opus 5 $0.00064 $0.00966
Sonnet 5 $0.00026 $0.00386
Haiku 4.5 $0.00013 $0.00193

Measured 5d ago against content hash bbb077154ee5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

strategy-kernel 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 5d 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.

strategy/strategy-kernel/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

strategy-kernel

Most documents called "strategy" are not strategy. They are a vision statement, a stack of financial targets, and a list of initiatives, glued together with ambition. Richard Rumelt's core insight: a strategy is a way through a difficulty, an approach to overcoming an obstacle. If there is no named obstacle and no coherent way through it, there is no strategy, no matter how inspiring the deck.

This skill does two jobs:

  1. Diagnose an existing "strategy" and tell the truth about whether it is one.
  2. Build a real strategy from a situation using the kernel.

The kernel (Rumelt)

Every good strategy has three parts. Write them in this order, never skip one.

  1. Diagnosis. What is actually going on? Name the single most important challenge or obstacle. Cut through the noise of the situation to the crux. A good diagnosis is often a metaphor or a reframe that makes the path forward suddenly obvious ("we are not a search company, we are being disrupted by mobile"). If you cannot state the challenge in a sentence or two, you do not understand it yet.

  2. Guiding policy. The overall approach chosen to cope with or overcome the obstacle named in the diagnosis. It is a signpost, not a goal. It rules things OUT. It creates advantage by concentrating effort. "Compete on integrated logistics, not on price" is a guiding policy. "Be number one in the market" is not — it names no approach.

  3. Coherent actions. The concrete steps, coordinated with one another, that carry out the guiding policy. "Coherent" is the operative word: the actions must reinforce each other and not fight for the same resources or pull in opposite directions. A list of independent initiatives that each sound good but do not compound is not coherent action.

The power of a strategy comes from coherence and concentration, not from the individual cleverness of any one action. A mediocre action that fits the policy beats a brilliant action that contradicts it.

Read the full file on GitHub · 96 lines

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. 5d ago First seen · 96 lines · 129 tokens per session scan A bbb077154ee5

Subscribe to this mod's changes

strategy-kernel is a skill published in the GitHub repository exiao/pm-skills (9 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 129 tokens to every session and 1,932 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens