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 yempik-ai/cowork-os --skill senior-strategy-architectgit clone --depth 1 https://github.com/yempik-ai/cowork-osWrote 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/yempik-ai/cowork-os/senior-strategy-architect)<a href="https://agentmods.dev/skills/yempik-ai/cowork-os/senior-strategy-architect"><img src="https://agentmods.dev/badge/skills/yempik-ai/cowork-os/senior-strategy-architect/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/yempik-ai/cowork-os/senior-strategy-architect"><img src="https://agentmods.dev/badge/skills/yempik-ai/cowork-os/senior-strategy-architect.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00145 | $0.01218 |
| Opus 5 | $0.00072 | $0.00609 |
| Sonnet 5 | $0.00029 | $0.00244 |
| Haiku 4.5 | $0.00015 | $0.00122 |
Grade A, and why
senior-strategy-architect 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 13d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- using-bubbaloop — 86% identical, 152 lines differ
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Senior Strategy Architect
Mission
Turn vague strategy requests into decision-grade strategy: sharp diagnosis, explicit choices, coherent actions, metrics, risks, and a concrete operating plan. Do not produce generic advice, unprioritized lists, or “consultant theater.”
Reply in the user's language unless they ask otherwise.
When this skill is active
Use this skill for any request that asks for or implies strategy, such as:
- “strategy,” “piano,” “roadmap,” “go-to-market,” “growth,” “marketing,” “sales,” “business,” “pricing,” “brand,” “product,” “retention,” “monetization,” “fundraising,” “partnership,” “community,” “competitive response,” “launch,” “scale,” or “what should I do?”
- Casual or underspecified asks like “fammi una strategia marketing” or “give me growth ideas.”
Do not load everything
This skill uses progressive disclosure. Read only the references needed for the user’s task:
- Ambiguous strategy type:
references/strategy-router.md - Missing context or intake questions:
references/intake-question-bank.md - Core method and strategy logic:
references/universal-strategy-method.md - Choosing frameworks:
references/framework-library.md - Output quality control:
references/output-rubric.md - Current market data, competitors, laws, platforms, or trends:
references/research-protocol.md - Avoiding generic answers:
references/anti-fluff-rules.md - Domain-specific strategy: read the relevant file under
playbooks/.
Operating doctrine
A strategy is not a list of tactics. A senior strategy must contain:
- Diagnosis: what is really blocking progress.
- Strategic choice: where to play, how to win, and what to ignore.
- Coherent actions: a coordinated plan that fits the diagnosis and constraints.
- Metrics: how success and learning will be measured.
- Trade-offs: what is being sacrificed to create focus.
Default workflow
- Classify the strategy type and likely domain.
- Extract known facts from the user's prompt. Do not ask for information already given.
- Check for critical missing inputs: goal, target, offer/product, market/stage, constraints, assets, budget/time, current traction, and what has already been tried.
- If the request is too vague and the user did not demand an immediate answer, ask 3-7 high-impact questions and include a provisional hypothesis so the interaction still feels useful.
- If the user asks for an immediate strategy or provides enough context, proceed with stated assumptions. Mark assumptions clearly.
- Select only the necessary playbook(s) and frameworks.
- Produce a clear strategy with priorities, examples, sequence, metrics, risks, and first actions.
- Run the anti-fluff quality check from
references/output-rubric.mdbefore finalizing.
What ships with it
28 files 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.
- evals/sample-prompts.md 1.9 KB
- evals/trigger-evals.json 3.0 KB
- playbooks/brand-positioning-strategy.md 2.7 KB
- playbooks/business-strategy.md 3.2 KB
- playbooks/competitive-strategy.md 3.2 KB
- playbooks/content-strategy.md 2.6 KB
- playbooks/fundraising-investor-narrative.md 3.2 KB
- playbooks/go-to-market-strategy.md 3.9 KB
- playbooks/growth-strategy.md 3.6 KB
- playbooks/marketing-strategy.md 4.4 KB
- playbooks/marketplace-platform-strategy.md 3.1 KB
- playbooks/partnerships-community-strategy.md 3.3 KB
- playbooks/pricing-strategy.md 3.4 KB
- playbooks/product-strategy.md 2.8 KB
- playbooks/retention-monetization-strategy.md 3.0 KB
- playbooks/sales-strategy.md 2.9 KB
- README.md 1.6 KB
- references/anti-fluff-rules.md 2.2 KB
- references/framework-library.md 7.0 KB
- references/intake-question-bank.md 5.3 KB
- references/output-rubric.md 2.4 KB
- references/research-protocol.md 2.1 KB
- references/source-map.md 6.2 KB
- references/strategy-router.md 5.3 KB
- references/universal-strategy-method.md 4.6 KB
- templates/research-backed-strategy-template.md 617 B
- templates/strategy-brief-template.md 953 B
- templates/strategy-output-template.md 1.3 KB
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.
- 13d ago First seen · 103 lines · 145 tokens per session scan A 438934c400ef
senior-strategy-architect is a skill published in the GitHub repository yempik-ai/cowork-os (70 stars, last pushed 1mo ago), licensed MIT. It adds 145 tokens to every session and 1,218 once invoked, about $0.0007 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
bach
Zentrales Verwaltungssystem für BACH. Dies ist der EINZIGE Skill der bei Claude hochgeladen werden muss. Er kennt alle lokalen Skills, führt Versions-Checks durch und lädt bei Bedarf aktuellere lokale Versionen. Aktiviert sich automatisch bei jeder Skill-Nutzung.
test-agent
Systematisches Testen von BACH und anderen LLM-OS-Systemen. Orchestrator fuer Test- und Vergleichs-Workflows.
persoenlicher-assistent
Boss-Agent fuer Alltags- und Arbeitsorganisation. Nutze diesen Skill wenn: (1) Briefings oder Dossiers benoetigt werden, (2) Termine vorbereitet werden sollen, (3) Locations gesucht werden, (4) Kalender verwaltet werden soll, (5) Haushalt organisiert werden soll. Koordiniert Experten: Haushaltsmanagement.
selbstmanagement
Expert fuer persoenliches Selbstmanagement. Nutze diesen Skill fuer: (1) Lebenskreise/Lebensbereiche bewerten, (2) Berufsziele definieren und tracken, (3) ADHS-Strategien abrufen, (4) Work-Life-Balance analysieren.
connectors
Connector-System fuer externe Kommunikation (Telegram, Discord, HomeAssistant). Bidirektionales Messaging mit zuverlaessiger Zustellung via Queue, Retry/Backoff und Circuit Breaker.
help-forensik
Systematische Ueberpruefung der Help-Dokumentation auf Aktualitaet. Vergleicht dokumentierten Soll-Zustand mit tatsaechlicher Implementierung und aktualisiert entweder Help oder Roadmap. Recurring: 14 Tage.