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 skills add EliasOulkadi/shokunin --skill strategygit clone --depth 1 https://github.com/EliasOulkadi/shokuninWrote 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/eliasoulkadi/shokunin/strategy)<a href="https://agentmods.dev/skills/eliasoulkadi/shokunin/strategy"><img src="https://agentmods.dev/badge/skills/eliasoulkadi/shokunin/strategy/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/eliasoulkadi/shokunin/strategy"><img src="https://agentmods.dev/badge/skills/eliasoulkadi/shokunin/strategy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00042 | $0.02845 |
| Opus 5 | $0.00021 | $0.01422 |
| Sonnet 5 | $0.00008 | $0.00569 |
| Haiku 4.5 | $0.00004 | $0.00284 |
Grade A, and why
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 10d 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 — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Strategy
Structured thinking for brainstorming, prompt engineering, and decision making.
Workflow
Step 1: Intake & Framing
Extract the user's core need and classify it into one of three tracks:
| Track | Trigger | Output |
|---|---|---|
| Decision | "Should I...", "Which option...", "Help me choose..." | Scored recommendation with rationale and runner-up tradeoff |
| Ideation | "Brainstorm...", "Generate ideas for...", "What are ways to..." | Prioritized list of ideas with convergent selection |
| Clarity | "How do I think about...", "Improve this prompt", "Reframe..." | Restructured framing, 7-dimension prompt, or first-principles breakdown |
If the user's need spans multiple tracks, run them sequentially: Clarity → Ideation → Decision.
Step 2: Select Framework
For Decision track: Choose ICE if speed matters, Impact/Effort matrix if resources are constrained, First Principles if the problem feels stuck or assumed, Pre-Mortem if the decision is high-stakes and irreversible.
For Ideation track: Start with brainwriting (quantity). If ideas stall, inject SCAMPER or reverse brainstorming. Never open with free association for groups of 3+ — dominant voices take over.
For Clarity track: Run the 7-dimension prompt diagnosis. Identify which dimensions are weak (0-3 on a 1-10 scale). Rewrite the prompt addressing the weakest dimensions first.
Step 3: Execute Framework
Follow the framework protocol from its dedicated section below. Timebox strictly:
- Decision: 20 min (5 min framing, 10 min scoring, 5 min decision)
- Ideation: 60 min (divergent 30 min, cluster 10 min, convergent 20 min)
- Clarity: 10 min (diagnose 3 min, rewrite 5 min, changelog 2 min)
Step 4: Document & Deliver
Every strategy output must include:
- The chosen framework and why it was selected
- The raw output (scores, ideas, rewritten prompt)
- One recommended action with owner + next step + deadline
- One explicitly rejected alternative and the reason
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.
- 10d ago First seen · 272 lines · 42 tokens per session scan A d9a6000127d5
strategy is a skill published in the GitHub repository EliasOulkadi/shokunin (113 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 2,845 once invoked, about $0.0002 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
ai-engineering-toolkit
6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
ideogram4
Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…
llm-patterns
AI-first application patterns, LLM testing, prompt management.
prompt-cache-optimizer
Audit and optimize Pisper system-prompt and tool-schema token overhead while preserving stable prompt-cache prefixes, permissions, and runtime behavior. Invoke only for explicit prompt or tool-context optimization work.
nativeprompt
A prompt editor that adapts a user's request to the rules of a selected coding model, such as Claude Code, Codex, Gemini CLI, or GPT-5.
coding-agents-prompt-authoring
To author, adapt, review, and validate prompts (skills, agents, workflows, rules, etc.) with brief, contracts, and a validation pack.