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 atman-33/workhub --skill strategy-decomposegit clone --depth 1 https://github.com/atman-33/workhubWrote 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/atman-33/workhub/strategy-decompose)<a href="https://agentmods.dev/skills/atman-33/workhub/strategy-decompose"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/strategy-decompose/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/atman-33/workhub/strategy-decompose"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/strategy-decompose.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 | $0.00085 | $0.01208 |
| Opus 5.5 | $0.00034 | $0.00483 |
| Sonnet 5.5 | $0.00017 | $0.00242 |
| Haiku 4.5 | $0.00009 | $0.00121 |
Grade A, and why
strategy-decompose 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 1mo 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
strategy-decompose — turn an upper strategy into your organization's target states
The output is not a policy. It is the material a policy is written from: the states your organization has to reach for the upper strategy to hold.
Work through phases 1-5 in order. Do not start a phase until the previous phase's completion criterion is met.
Settle the destinations first
Before any work, pin down two locations. Ask the owner if either is unclear.
- Where the notes go — a Markdown home the owner and future sessions read
(in a workhub vault:
projects/NNNN-<slug>/dev-notes/, or thebacklog/item the decomposition belongs to) - Where the xlsx goes — somewhere the owner can actually open it. If the notes live in a vault the owner reads through Obsidian, the xlsx does not belong there; put it on their cloud drive
Always write to the AI-owned workbook (<name>-draft.xlsx), never to the
owner's (<name>.xlsx). See references/xlsx-format.md.
Phase 1 — take in the upper strategy
- Read the material. Store the original verbatim — never a summary. In a
vault,
projects/NNNN-<slug>/research/ - Identify the hierarchy (e.g. company → department → team → your unit). For each level write down what it commits to and where it gets measured
- Capture spoken context too (kickoff Q&A, decisions made in a meeting). Later phases lean on "agreed but not in the document" material
Completion criterion: the original is stored, each level's objectives are listed, and you can say in one sentence which item your own organization hangs off.
Phase 2 — remove the unknowns (discussion)
An upper strategy is rarely decomposable as written: too abstract, subject omitted, no definition behind a number. Close that gap here.
- For every sentence of the upper strategy, ask yourself: can I state, in one sentence, the state in which it is achieved?
- Turn each sentence you cannot state into a question. Every question carries a recommended answer so the owner only has to choose
- At most 5 questions per round — more and the answers get careless
- Append the answers next to the stored original, recording how each question was settled
What ships with it
4 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.
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.
- 1mo ago Changed 384f608f2bf8
- 1mo ago Changed 09aea9add393
- 1mo ago Changed · +1 lines 950632b7e499
- 1mo ago First seen · 110 lines · 85 tokens per session scan A a72f2dbb257d
strategy-decompose is a skill published in the GitHub repository atman-33/workhub (3 stars, last pushed 2d ago), licensed MIT. It adds 85 tokens to every session and 1,208 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
aetox-audit-xls
ตรวจเวิร์กบุ๊กที่คนอื่นทำมา ก่อนเชื่อตัวเลขในนั้นหรือส่งต่อให้ใครใช้ หา error, ค่าคงที่ฝังในสูตร, สูตรที่หลุดแพตเทิร์น, ช่วง SUM ที่ขาดแถว, สูตรที่ถูกวางทับด้วยค่า และงบที่ไม่บาลานซ์.
aetox-clean-data-xls
ล้างข้อมูลที่เละก่อนเอาไปคำนวณ รวมยอด หรือ pivot ช่องว่างหัวท้าย ตัวพิมพ์ไม่ตรงกัน ตัวเลขที่ถูกเก็บเป็นข้อความ วันที่คนละฟอร์แมตในคอลัมน์เดียว แถวซ้ำ และตัวอักษรเพี้ยน.
learn
Ingests an external data source into the Second Brain. Fetches content from Confluence, Google Docs, GitHub repositories, remote URLs, or any local file format supported by docling (DOCX, PPTX, XLSX, PDF, HTML, EPUB, images, Markdown, CSV, and more), converts non-markdown formats to markdown via docling, runs the…
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
lark-base
A guide for managing Lark Base, Feishu's spreadsheet-like database and workspace tool. It covers tables, fields, records, views, formulas, forms, dashboards, applications, workflows, and permissions.
tencent-docs
A skill for creating, reading, editing, searching, and managing Tencent Docs, an online document and spreadsheet service.