think

think is a skill for Claude Code, Codex from ironyjk/strategy-frameworks. It costs 65 tokens per session (4,206 once invoked), scanned A, original, MIT.

A strategic problem-solving assistant that chooses from established business analysis methods based on the problem you describe.

In plain words
What is it for?
Use it to examine bottlenecks, conflicts, recurring problems, implementation plans, investment choices, and other business decisions.
Why use it?
It removes the need to know which business framework fits a particular challenge.

Skill for Claude CodeCodex

Part of the strategy-frameworks plugin — 27 skills shipped together

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/ironyjk/strategy-frameworks/think
Any agent
npx skills add ironyjk/strategy-frameworks --skill think
Clone the repo
git clone --depth 1 https://github.com/ironyjk/strategy-frameworks

Made for: Claude Code, Codex.

Or install strategy-frameworks, the plugin that ships this one along with the rest of its 27 skills.

Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,206 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 $0.00065 $0.04206
Opus 5 $0.00032 $0.02103
Sonnet 5 $0.00013 $0.00841
Haiku 4.5 $0.00006 $0.00421

Measured 3d ago against content hash 59f1341845a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

think 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 3d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (check-update.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

think/SKILL.md · 245 lines

How it starts

The opening of the file, as written. The whole thing — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Strategic Thinking Agent — 47 Tools, One Entry Point

You are a meta-reasoning agent. When the user describes a problem, you:

  1. Classify the problem type
  2. Select the best framework(s)
  3. Execute them (via Skill tool)
  4. Synthesize a unified answer

Problem Classification → Framework Selection

Analyze the user's problem and match it to one or more categories:

Detection Matrix

Signal in the problem Primary Framework Secondary
"bottleneck", "can't keep up", "limiting factor", "constraint" TOC: Five Steps TOC: CRT
"conflict", "either-or", "trade-off", "can't have both" TOC: EC TRIZ: Contradiction
"why does this keep happening", "recurring problem", "root cause" TOC: CRT Systems Thinking
"will this solution work?", "side effects", "unintended consequences" TOC: FRT Systems Thinking
"how to implement", "step by step", "execution plan" TOC: TT Drucker: MBO
"resistance to change", "people won't accept", "buy-in" TOC: Buy-in Design Thinking
"scheduling", "project delay", "multi-project" TOC: CCPM TOC: DBR
"should we invest?", "ROI", "make vs buy" TOC: Throughput Porter: Strategy
"technical problem", "engineering contradiction", "improve X without degrading Y" TRIZ: Contradiction TRIZ: Matrix → 40P
"ideal solution", "perfect outcome", "zero cost" TRIZ: IFR First Principles
"simplify", "remove complexity", "too many components" TRIZ: Trimming First Principles
"what's next", "future technology", "evolution" TRIZ: Evolution Wardley
"hidden resource", "underutilized asset" TRIZ: Resources Blue Ocean
"where should we compete", "build vs buy", "strategic position" Wardley Porter: Forces
"competitor entering", "price war", "industry analysis" Porter: Five Forces Blue Ocean
"competitive advantage", "value chain", "cost vs differentiation" Porter: Strategy Wardley
"new market", "escape competition", "create demand" Blue Ocean Design Thinking
"customer problem", "user experience", "what do they really need" Design Thinking Drucker: 5Q
"why is it so expensive", "everyone says it can't be done", "assumption" First Principles TRIZ: IFR
"fast decision needed", "crisis", "competitor moving fast" OODA TOC: Five Steps
"system behaving unexpectedly", "feedback loop", "fix made it worse" Systems Thinking TOC: CRT
"goals", "objectives", "what should we focus on", "KPI" Drucker: MBO BSC
"measure performance", "balanced view", "strategy execution" BSC Drucker: MBO
"mission", "purpose", "who is our customer" Drucker: 5Q Design Thinking
"effectiveness", "time management", "priorities" Drucker: Effective TOC: Five Steps
"portfolio", "which business to invest", "star vs dog", "cash cow", "question mark", "resource allocation" BCG Matrix Ansoff Matrix
"organization not aligned", "culture problem", "merger integration", "restructuring" McKinsey 7S Kotter
"strengths", "weaknesses", "opportunities", "threats", "external environment" SWOT-PESTEL Porter: Forces
"how to grow", "new market or new product", "diversification", "expansion" Ansoff Matrix Blue Ocean
"disruption", "startup threat", "incumbent at risk", "technology shift" Disruptive Innovation Scenario Planning
"uncertain future", "multiple scenarios", "what if", "black swan", "geopolitics", "long-term planning", "strategic foresight" Scenario Planning Real Options
"who is our target customer", "segmentation", "positioning", "brand perception" STP Marketing Mix
"marketing plan", "pricing", "distribution", "promotion", "4P", "7P" Marketing Mix STP
"why do customers buy", "customer motivation", "switching behavior", "hire a product" JTBD Design Thinking
"business model", "revenue model", "value proposition", "canvas" BMC Lean Startup
"change management", "people resist change", "transformation", "adoption" Kotter McKinsey 7S
"OKR", "goal setting", "alignment", "key results", "quarterly goals" OKR Drucker: MBO
"MVP", "validate idea", "startup", "pivot", "experiment", "hypothesis" Lean Startup BMC
"invest or wait", "option value", "staged investment", "defer decision" Real Options TOC: Throughput
"competitor reaction", "price war", "strategic interaction", "game", "bluff" Game Theory Porter: Forces
"present findings", "structure communication", "executive summary", "report" Pyramid Principle BSC
"what is our advantage", "unique resource", "VRIO", "core competence", "capability" RBV Porter: Strategy
"어떻게 키울까", "성장 전략", "사업 확장" Ansoff Matrix Blue Ocean
"경쟁사가 무서워", "시장 잠식", "저가 경쟁자" Disruptive Innovation Porter: Forces
"뭘 해야 할지 모르겠어", "막막하다", "방향을 못 잡겠어" Drucker: 5Q First Principles

Read the full file on GitHub · 245 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. 3d ago First seen · 245 lines · 65 tokens per session scan A 59f1341845a8

Subscribe to this mod's changes

think is a skill published in the GitHub repository ironyjk/strategy-frameworks (11 stars, last pushed 4mo ago), licensed MIT. It adds 65 tokens to every session and 4,206 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.

Related

Other skills, from other repositories

new-venture

This skill should be used when the user wants to start working on a new business idea, product, startup, or client engagement — e.g. "I have a new idea", "set up a new venture", "register a new client", "let's analyze this business", "ایده جدید دارم", "یه بیزینس جدید", "ونچر جدید بساز", "کلاینت جدید", "می‌خوام روی این…

heyparsadev/claude-venture-plugin · 118 tokens

ceo-skill

CEO decision-making advisor and strategic thinking partner. Use when users need help with executive-level decisions including strategy, resource allocation, risk assessment, competitive positioning, organizational design, M&A evaluation, crisis response, OKR/KPI setting, fundraising, stakeholder management, cognitive…

AIPMAndy/CEOskill · 133 tokens

gtm

This skill should be used when the user asks for go-to-market strategy, positioning, launch planning, channel strategy, pricing strategy, or messaging — e.g. "build a GTM strategy", "how should we launch", "which channels should we use", "positioning for my product", "pricing strategy", "استراتژی ورود به بازار"…

heyparsadev/claude-venture-plugin · 131 tokens

review

This skill should be used when the user wants an honest overall assessment of a venture — a board-style review, go/no-go decision, kill-pivot-persevere call, investment-readiness check, or periodic check-in — e.g. "review my whole venture", "should I continue with this", "be brutally honest about this business"…

heyparsadev/claude-venture-plugin · 150 tokens

competitors

This skill should be used when the user asks for competitor analysis, competitive landscape, battlecards, positioning maps, or "who else does this" — e.g. "analyze my competitors", "competitive analysis for X", "build a battlecard", "who are the alternatives", "تحلیل رقبا", "رقیب‌های این محصول کیان", "رقبا رو بررسی…

heyparsadev/claude-venture-plugin · 119 tokens

customers

This skill should be used when the user wants customer discovery work — interview guides, problem validation, personas, jobs-to-be-done, or synthesizing interview/survey feedback — e.g. "make a customer interview guide", "how do I validate this problem", "build personas", "analyze my interview notes", "synthesize user…

heyparsadev/claude-venture-plugin · 132 tokens