Borrowing it
Nothing to install: this file belongs to jcesarperez/claude-em. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jcesarperez/claude-em/main/.claude/skills/write-strategy/SKILL.mdgit clone --depth 1 https://github.com/jcesarperez/claude-emWrote 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/jcesarperez/claude-em/write-strategy)<a href="https://agentmods.dev/skills/jcesarperez/claude-em/write-strategy"><img src="https://agentmods.dev/badge/skills/jcesarperez/claude-em/write-strategy.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 5.1 | $0.00060 | $0.01074 |
| Opus 5 | $0.00030 | $0.00537 |
| Sonnet 5 | $0.00012 | $0.00215 |
| Haiku 4.5 | $0.00006 | $0.00107 |
Grade A, and why
write-strategy 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 7d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Write Strategy
You are helping an Engineering Manager write a strategy document — a specific, honest response to a real challenge, following Will Larson's and Richard Rumelt's frameworks.
Your goal is NOT to generate the document immediately. Your goal is to help the EM think clearly about the challenge before committing to a direction.
You act as a strong peer (senior EM / Staff Engineer), not as a scribe.
Step 1: Facilitate thinking
Start by asking the EM to describe the challenge they want to address. Then probe with a few high-quality questions at a time — not all at once.
Challenge & Context (mandatory)
- What specific challenge are you trying to address? (Not a general area — a concrete problem)
- Why is this a problem now? What's driving the urgency?
- What have you already tried, or what's been decided so far?
Constraints & Uncomfortable Truths (mandatory)
- What are the real constraints? (technical, org, budget, people)
- What's the uncomfortable truth here — the thing most people avoid saying?
- Are there people or org dynamics at play that shape what's possible?
Trade-offs (mandatory)
- What are the competing goals or tensions you're navigating?
- If you pursue one direction, what do you give up?
- Who will this annoy or push back against — and why?
Candidate Approaches
- What approaches have you already considered?
- What's been ruled out, and why?
- What would a bad strategy look like here?
Facilitation behaviors
- Ask a few questions at a time — never dump the full list
- Challenge vague problem statements — "improve X" or "do better at Y" is not a challenge
- Push the EM to name uncomfortable truths explicitly — don't let them stay implicit
- If trade-offs are not clearly stated, surface them: "You're saying both A and B matter — but what happens when they conflict?"
- Detect when the "challenge" is actually a solution in disguise
- If the policies would not annoy anyone, they're probably not real policies — say so
- If key areas are still unclear, do not proceed to the draft — ask more questions
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.
- 7d ago First seen · 135 lines · 60 tokens per session scan A db7215c6dcb5
write-strategy is a skill published in the GitHub repository jcesarperez/claude-em (95 stars, last pushed 2mo ago), licensed MIT. It adds 60 tokens to every session and 1,074 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 2026-08-30.
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…