memory-update

memory-update is a command for Claude Code from yempik-ai/cowork-os. It costs 42 tokens per session (463 once invoked), scanned A, original, MIT.

A workspace memory-maintenance protocol that checks the current task for decisions, assumptions, risks, questions, tasks, and other lasting information. It writes each item to the appropriate project file.

In plain words
What is it for?
Updating decision logs, assumptions, risks, marketing notes, website backlogs, analytics records, opportunities, and other ongoing project documentation.
Why use it?
It keeps useful context from being lost when a conversation ends. It also separates confirmed decisions from open questions and unvalidated assumptions.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the cowork-os plugin — 4 skills, 7 commands shipped together

Good fit Updating decision logs, assumptions, risks, marketing notes, website backlogs, analytics records, opportunities, and other ongoing project documentation.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/yempik-ai/cowork-os/memory-update
Install

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.

Clone the repo
git clone --depth 1 https://github.com/yempik-ai/cowork-os

Made for: Claude Code.

Or install cowork-os, the plugin that ships this one along with the rest of its 4 skills, 7 commands.

Wrote 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.

agentmods badge for memory-update

README.md
[![agentmods](https://agentmods.dev/badge/commands/yempik-ai/cowork-os/memory-update/github.svg)](https://agentmods.dev/commands/yempik-ai/cowork-os/memory-update)
Your own site
<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.

agentmods 80×15 button for memory-update

Your own site · 80×15
<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>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 463 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 9d ago against content hash 29e2979f044b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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.

plugins/cowork-os/commands/memory-update.md · 42 lines

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.md if present, else decisions/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/ or reviews/
  • website tasks: website/backlog.md
  • website, SEO, UX, conversion notes: website/website_notes.md
  • risks: strategy/risks.md if present, else decisions/open_questions.md
  • opportunities: business-development/ if present, else marketing/strategy.md
  • partnerships: business-development/partnerships.md if present, else decisions/open_questions.md
  • operational reviews: reviews/weekly_review.md or reviews/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:
Changes

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.

  1. 9d ago First seen · 42 lines · 42 tokens per session scan A 29e2979f044b

Subscribe to this mod's changes

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.