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 instructions/chefjefff/mckinsey-problem-solving/claude-mdgit clone --depth 1 https://github.com/chefjefff/mckinsey-problem-solvingWrote 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/instructions/chefjefff/mckinsey-problem-solving/claude-md)<a href="https://agentmods.dev/instructions/chefjefff/mckinsey-problem-solving/claude-md"><img src="https://agentmods.dev/badge/instructions/chefjefff/mckinsey-problem-solving/claude-md.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 | $0.00893 | $0.00893 |
| Opus 5 | $0.00447 | $0.00447 |
| Sonnet 5 | $0.00179 | $0.00179 |
| Haiku 4.5 | $0.00089 | $0.00089 |
Grade A, and why
mckinsey-problem-solving CLAUDE.md 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🧭 HOW WE THINK — McKinsey 7-Step Problem Solving
/problem-solving is the operating default for any complex question, strategic diagnosis, analysis, or "should we do X?" decision.
Any non-trivial thinking task — market analysis, root-cause diagnosis, strategic recommendations, competitive positioning, uncertainty management, "why is this happening?", "what should we do?" — must be structured using the /problem-solving skill.
The 7 steps
- Define the problem (SMART+, problem worksheet, "porpoise" to refine)
- Disaggregate with MECE logic trees (component, deductive, inductive, hypothesis, decision, ROIC)
- Prioritize via 2x2 impact × ability-to-move matrix, prune the tree
- Build a workplan (hypothesis-driven, knock-out order, dummy the chart)
- Conduct analysis — heuristics first (Occam, 80:20, Rule of 72, expected value, 5 Whys) → big guns only if needed (regression, Bayesian, ML, game theory)
- Synthesize findings with pyramid principle, visualize, surface cross-cutting insights
- Tell the story via SCR (Situation/Complication/Resolution), storyboard, lead with answer
Cleaving frames (try multiple, pick what reveals the most)
Business: ROIC/profit lever, price/volume, principal/agent, assets/options, collaborate/compete, supply/demand.
Societal: regulate/incent, equality/liberty, mitigate/adapt, incidence/severity.
Personal: work/play, near-term/long-term, financial/non-financial.
Bias fighting
Obligation to dissent • Multiple trees • "What would you have to believe?" • Pre-mortem analysis • Distributed voting • Perspective-taking • Red Team/Blue Team.
The test (run before handing over any analysis or recommendation)
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 · 75 lines · 893 tokens per session scan A f8c1a6e79107
mckinsey-problem-solving CLAUDE.md is an instructions file published in the GitHub repository chefjefff/mckinsey-problem-solving (12 stars, last pushed 4mo ago), licensed MIT. It adds 893 tokens to every session, about $0.0045 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 instructions, from other repositories
nextclaw AGENTS.md
AGENTS.md instructions for Peiiii/nextclaw, covering nextclaw ai 常驻内核, 产品愿景, 沟通与推进, 深思与目标模式 and 协作与 git 安全.
Commonly-used-high-value-skills AGENTS.md
AGENTS.md instructions for seaworld008/Commonly-used-high-value-skills, covering repository agent instructions, architecture overview, installation root by client, golden rules and automated operations (sop for ai agents).
slipway AGENTS.md
AGENTS.md instructions for signalridge/slipway, covering slipway agent principles, user owns the process, investigate before clarifying, report, do not certify and maintain the whole surface.
nobrainer-tech-skills copilot-instructions.md
Copilot instructions for nobrainer-tech/nobrainer-tech-skills: The fifteen canonical Agent Skills are under skills/. Read the relevant skills/ /SKILL.md before changing a skill; retired predecessors exist only in Git history.
agentic-rd-skill AGENTS.md
AGENTS.md instructions for TheStreamCode/agentic-rd-skill, covering repository instructions, purpose and sources of truth, repository invariants, implementation style and documentation synchronization.
ccpr CLAUDE.md
Claude Code instructions for jonase47/ccpr, covering global preferences (local, interactive mode), language & communication, personal context, infrastructure and code standards.