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/memory-update)<a href="https://agentmods.dev/commands/yempik-ai/cowork-os/memory-update"><img src="https://agentmods.dev/badge/commands/yempik-ai/cowork-os/memory-update/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/memory-update"><img src="https://agentmods.dev/badge/commands/yempik-ai/cowork-os/memory-update.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 | $0.00042 | $0.00463 |
| Opus 5 | $0.00021 | $0.00231 |
| Sonnet 5 | $0.00008 | $0.00093 |
| Haiku 4.5 | $0.00004 | $0.00046 |
Grade A, and why
memory-update 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:memory-update
Run the Memory Update protocol that keeps this workspace a living knowledge base instead of a disposable chat.
Before considering the current task done, check whether any of these emerged: decisions, open questions, assumptions, risks, tasks, commercial opportunities, roadmap updates, stale information, source conflicts. If something relevant emerged, update the right file.
Where to write what
- confirmed decisions:
decisions/decisions_log.md - open questions:
decisions/open_questions.md - unvalidated assumptions:
context/assumptions.mdif present, elsedecisions/open_questions.md - positioning insight:
context/positioning.md - tone-of-voice notes:
context/tone_of_voice.md - general marketing insight:
marketing/strategy.md - campaign insight:
marketing/campaigns.md - content ideas:
marketing/content.md - data, analytics, reports:
analytics/orreviews/ - website tasks:
website/backlog.md - website, SEO, UX, conversion notes:
website/website_notes.md - risks:
strategy/risks.mdif present, elsedecisions/open_questions.md - opportunities:
business-development/if present, elsemarketing/strategy.md - partnerships:
business-development/partnerships.mdif present, elsedecisions/open_questions.md - operational reviews:
reviews/weekly_review.mdorreviews/maintenance_review.md
If you cannot edit files directly, do not skip the Memory Update: return a section with the recommended changes (file to update, content to add, content to change, content to verify, reason). If nothing changed, state it explicitly: "Memory Update: nothing to update."
Required end-of-task format
Memory Update
- Files updated:
- Decisions added:
- Open questions added:
- Assumptions added:
- Tasks added:
- Risks added:
- Opportunities added:
- Next actions:
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 · 42 lines · 42 tokens per session scan A 29e2979f044b
memory-update is a command published in the GitHub repository yempik-ai/cowork-os (70 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 463 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 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.