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 knowledge-transfergit 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/knowledge-transfer)<a href="https://agentmods.dev/skills/yempik-ai/cowork-os/knowledge-transfer"><img src="https://agentmods.dev/badge/skills/yempik-ai/cowork-os/knowledge-transfer/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/knowledge-transfer"><img src="https://agentmods.dev/badge/skills/yempik-ai/cowork-os/knowledge-transfer.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 | $0.00148 | $0.01843 |
| Opus 5 | $0.00074 | $0.00922 |
| Sonnet 5 | $0.00030 | $0.00369 |
| Haiku 4.5 | $0.00015 | $0.00184 |
Grade A, and why
knowledge-transfer 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Transfer, the interview that builds the company brain
You interview one person and turn their tacit know-how into the workspace, so the team and other agents can read, apply and correct it.
The hard truth this skill exists for: people cannot narrate a process they have automated. The better someone is at a job, the less they can explain it, because they run it on autopilot. Ask "how do you do X" and you get the official, abstract version (the manual), not the real one (the one full of "well, it depends"). Your job is not to collect answers. It is to make the tacit observable. Interview in the user's language.
Non-negotiables
- One question at a time. Never a volley. Short questions.
- Never invent. Every rule carries a source (interview, date, who) and a confidence. If something is unknown, say so and park it in
decisions/open_questions.md. - After the first 3-4 framing questions, stop using a list. Generate every next question from the person's last answer, aimed at its vaguest or most loaded part. A generic follow-up you could have asked anyone is a failure.
- Budget: about 15 minutes, 1 or 2 processes per session. Depth over coverage. The brain grows over more sessions, do not try to capture everything at once.
Step 1, frame (standard, 3-4 questions only)
- Who you are and your role, which single process we capture today.
- Objective: what must a new hire be able to do on their own within 2 weeks? (this fixes the scope)
- Which case is most frequent, and which one hurts most if done badly? (pick ONE to start)
- Start from a real episode: "Think of the LAST time you did this. Walk me through that specific time, step by step." Never start from the abstract "how do you usually do it".
Step 2, the probing loop (this is the actual skill)
For the chosen process, run this loop until you have concrete rules, then move to the next step or process. Each turn: read the last answer, pick the probe that attacks what is missing, ask ONE short question.
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 · 68 lines · 0 tokens per session scan A a0ced69b35b9
knowledge-transfer is a skill published in the GitHub repository yempik-ai/cowork-os (70 stars, last pushed 1mo ago), licensed MIT. It adds 148 tokens to every session and 1,843 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
voice-service
Voice Service fuer BACH - STT, TTS und Wake-Word-Erkennung. Portiert und erweitert aus BachForelle voice.py + ears.py. Version 1.1: Erweitert um File-Export und Piper-TTS.
DokuZentrum Service
Core Document Processing Service for BACH (Integration of DokuZentrum).
xlsx
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or…
tencent-docs
A skill for creating, reading, editing, searching, and managing Tencent Docs, an online document and spreadsheet service.
government-writing
A skill for writing formal Chinese government documents, including notices and opinions, in the required official format.
ima-skills
Tencent IMA OpenAPI skill for notes and knowledge-base operations. Use after the user connects IMA in Pinvou Plugin Center.