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 agentmods add skills/exiao/pm-skills/strategy-kernelnpx skills add exiao/pm-skills --skill strategy-kernelgit clone --depth 1 https://github.com/exiao/pm-skillsWrote 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/exiao/pm-skills/strategy-kernel)<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>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 | $0.00129 | $0.01932 |
| Opus 5 | $0.00064 | $0.00966 |
| Sonnet 5 | $0.00026 | $0.00386 |
| Haiku 4.5 | $0.00013 | $0.00193 |
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.
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:
- Diagnose an existing "strategy" and tell the truth about whether it is one.
- 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.
-
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.
-
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.
-
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.
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.
- 5d ago First seen · 96 lines · 129 tokens per session scan A bbb077154ee5
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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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.
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…
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…