cowork-mem

cowork-mem is a skill for Claude Code from MSApps-Mobile/claude-plugins. It costs 157 tokens per session (1,834 once invoked), scanned A, original, MIT.

A persistent memory system for Claude sessions that stores project decisions, file changes, insights, errors, and other notes in a local database.

In plain words
What is it for?
Use it to recall earlier sessions, search stored notes, save the reasons behind decisions, and preserve context across separate coding sessions.
Why use it?
It keeps useful context available after a session ends and can automatically record important activity. This reduces the need to reconstruct previous work.

Skill for Claude Code

Written for Claude Code: SessionStart hook event. Also seen: reads .claude/ paths.

Part of the cowork-mem plugin — 7 skills, 1 hook shipped together

Good fit Use it to recall earlier sessions, search stored notes, save the reasons…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/msapps-mobile/claude-plugins/cowork-mem
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.

Any agent
npx skills add MSApps-Mobile/claude-plugins --skill cowork-mem
Clone the repo
git clone --depth 1 https://github.com/MSApps-Mobile/claude-plugins

Made for: Claude Code.

Or install cowork-mem, the plugin that ships this one along with the rest of its 7 skills, 1 hook.

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 cowork-mem

README.md
[![agentmods](https://agentmods.dev/badge/skills/msapps-mobile/claude-plugins/cowork-mem.svg)](https://agentmods.dev/skills/msapps-mobile/claude-plugins/cowork-mem)
Your own site
<a href="https://agentmods.dev/skills/msapps-mobile/claude-plugins/cowork-mem"><img src="https://agentmods.dev/badge/skills/msapps-mobile/claude-plugins/cowork-mem.svg" alt="Measured on agentmods" height="20"></a>
Per session 157 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,834 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 $0.00157 $0.01834
Opus 5 $0.00078 $0.00917
Sonnet 5 $0.00031 $0.00367
Haiku 4.5 $0.00016 $0.00183

Measured 6d ago against content hash 2e49bbccd563, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

cowork-mem 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 6d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/memory_store.py, scripts/post_tool_capture.py, scripts/vector_search.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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-mem/skills/cowork-mem/SKILL.md · 218 lines

How it starts

The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cowork-Mem: Persistent Memory for Cowork

You have access to a persistent memory system that survives across Cowork sessions. It stores observations (decisions, file edits, insights, errors, notes) in a SQLite database with full-text search and semantic (TF-IDF) search, organized into sessions.

How It Works

Memory is automatic — you don't need to manually trigger it every session. Three session hooks run in the background:

  • SessionStart: auto-recalls the last session summary before you begin
  • PostToolUse: auto-captures meaningful file edits, bash commands, and task completions as they happen
  • PreCompact: saves a timestamped marker before context is compacted

This means the memory fills itself. Your job is to add the why — decisions, insights, errors — that the hook can't infer automatically.

The Memory Script

All memory operations go through a single script:

python3 {SKILL_DIR}/scripts/memory_store.py <command> [args]

The database lives at ~/.claude/.cowork-mem/memory.db and persists on the user's machine across sessions. The COWORK_MEM_DB environment variable overrides the default path if set.

In addition to keyword search, you have vector search using TF-IDF similarity:

COWORK_MEM_DB=~/.claude/.cowork-mem/memory.db \
python3 {SKILL_DIR}/scripts/vector_search.py "authentication middleware pattern" --limit 8

Use semantic search when:

  • You want conceptually related observations (not just keyword matches)
  • The user asks vague questions like "what do we know about auth?"
  • You're exploring what the memory knows about a topic before diving into a task

Core Workflow

1. Session Start — Recall First

The SessionStart hook auto-runs session-start before you begin. If memory was loaded, you'll already have context. If working manually:

python3 {SKILL_DIR}/scripts/memory_store.py session-start --project "project-name"

Briefly tell the user what you remember: "Last time we worked on X, we decided Y and were in the middle of Z." Keep it to 1-2 sentences — don't dump everything.

Read the full file on GitHub · 218 lines

Files

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.

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. 6d ago First seen · 218 lines · 157 tokens per session scan A 2e49bbccd563

Subscribe to this mod's changes

cowork-mem is a skill published in the GitHub repository MSApps-Mobile/claude-plugins (9 stars, last pushed 11d ago), licensed MIT. It adds 157 tokens to every session and 1,834 once invoked, about $0.0008 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 2026-08-31.

Related

Other skills, from other repositories

decision

Full decision lifecycle in Semantica � record, query, find precedents (hybrid/advanced), analyze influence, explain, insights dashboard, list, and record exceptions. Uses AgentContext, ContextGraph, DecisionQuery, CausalChainAnalyzer, DecisionRecorder.

semantica-agi/semantica · 55 tokens

session-handoff

Synthesizes the current session into a structured HANDOFF block for context transfer between sessions. Captures what was built, decisions made, and unresolved items.

SethGammon/Citadel · 35 tokens

optimizer

Framework-driven audit and optimizer for a Baalda vault. Applies 10 frameworks covering CLAUDE.md quality, wiki structure, compression, context rot, memory, progressive disclosure, hygiene, cross-file synthesis, architecture and discoverability, plus F10 Claude 5 rule rewriting. Every finding ships a concrete fix; the…

naveedharri/benai-skills · 215 tokens

agentic-os-obsidian

Set up an agentic OS inside an Obsidian vault — a configurable command-center dashboard with 5 auto-installed, bundled plugins (Dataview, CustomJS, Shell-commands, Terminal, Homepage), Home + per-profile + Vault Overview pages, KPI cards, sparklines, heatmap, task rollup, and a button bar wired to user-defined Claude…

naveedharri/benai-skills · 154 tokens

operator

Build and schedule a personalized Operator prompt that runs a Baalda vault as a second brain on a recurring cadence. Run it from inside the vault: it reads Context/ and CLAUDE.md first to infer org, team, brand voice and paths, then asks only the gaps (cadence, connectors, DM recipient, budgets, signature), writes the…

naveedharri/benai-skills · 156 tokens

skill-os-builder

Stand up a self-contained second-brain "OS" that lives entirely inside a Claude skill — a short SKILL.md router plus context files, no vault, cloud, or MCP server. Use when the user says "set up a skill OS", "build my second brain as a skill", "skill OS", or wants the simplest portable AI OS.

naveedharri/benai-skills · 75 tokens