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.
git 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/commands/yempik-ai/cowork-os/knowledge-transfer)<a href="https://agentmods.dev/commands/yempik-ai/cowork-os/knowledge-transfer"><img src="https://agentmods.dev/badge/commands/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/commands/yempik-ai/cowork-os/knowledge-transfer"><img src="https://agentmods.dev/badge/commands/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 | $0.00052 | $0.00445 |
| Opus 5 | $0.00026 | $0.00222 |
| Sonnet 5 | $0.00010 | $0.00089 |
| Haiku 4.5 | $0.00005 | $0.00044 |
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 9d 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.
What it actually says
/cowork-os:knowledge-transfer
Run a structured, objective-first interview and build the company brain from one person's knowledge. Interview in the user's language. Use context/tone_of_voice.md if present.
Who / what to capture: $ARGUMENTS. If empty, ask who you are interviewing and which process or area before starting.
Run these phases (one question at a time, never a volley):
- Setup: role, process/area, time available.
- Objective: what must a new hire do alone in 2 weeks? Which 3 cases are most frequent, which 3 most costly if mishandled?
- Process map: for each key process, step by step from request to closing; systems used and in what order; where they wait on someone.
- Laddering (the value): exceptions ("when do you NOT do it this way?"), decision criteria, typical new-hire mistakes, unwritten rules, what to never promise.
- Verify: mirror back 5-8 rules ("do X, except when Y, right?") and let them correct.
Then write into the workspace:
context/processes/<process>.md(readable step-by-step)context/glossary.md(internal terms)decisions/decisions_log.md(rules astrigger -> action+exceptions+source: interview, <date>+ confidence)decisions/open_questions.md(gaps to clarify)
Never invent. Every rule carries a source and a confidence; if unknown, say so. Optionally generate 5-10 test cases to check an agent applies the rules correctly.
End with a Memory Update listing what you wrote and where.
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.
- 9d ago First seen · 28 lines · 0 tokens per session scan A 6ff4713c1e5c
knowledge-transfer is a command published in the GitHub repository yempik-ai/cowork-os (70 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 445 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.
Other commands, from other repositories
help
Show everything the Obsidian Knowledge Agent can do, with every command and an example.
capture
Quickly save something as a single clean note in the right place — a link, a thought, an article, a snippet.
reflect
Reflect on recent work — log lessons to the journal and propose distilled rule updates for review.
query
Query the wiki under one of three postures — research, contradictor, synthesis. Trigger FR — interroger le wiki, consulter le wiki, rechercher dans le wiki, contredire une thèse, synthétiser ce qu'on sait.
claude-flow-memory
Interact with Claude-Flow memory system.
session-memory
Maintain context and learnings across Claude Code sessions for continuous improvement.