Cognee is an AI memory platform that stores information in a self-hosted knowledge graph so agents can retain context across sessions. It ingests data, connects related information, and helps agents retrieve it for reasoning and actions. The catalogue includes skills and instructions that extend agent workflows around Cognee.
Borrowing it
Nothing to install: this file belongs to topoteretes/cognee. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/topoteretes/cognee/main/.agents/skills/google-workspace-memory/SKILL.mdgit clone --depth 1 https://github.com/topoteretes/cogneeWrote 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/topoteretes/cognee/google-workspace-memory)<a href="https://agentmods.dev/skills/topoteretes/cognee/google-workspace-memory"><img src="https://agentmods.dev/badge/skills/topoteretes/cognee/google-workspace-memory/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/topoteretes/cognee/google-workspace-memory"><img src="https://agentmods.dev/badge/skills/topoteretes/cognee/google-workspace-memory.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 | $0.00087 | $0.00902 |
| Opus 5.5 | $0.00035 | $0.00361 |
| Sonnet 5.5 | $0.00017 | $0.00180 |
| Haiku 4.5 | $0.00009 | $0.00090 |
Grade A, and why
google-workspace-memory 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 7d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Workspace memory
Runs the Google Workspace memory cookbook in examples/cookbooks/google_workspace_memory/.
It remembers the user's primary calendar, newest inbox emails and one Drive folder in the
cognee dataset google_workspace_memory, then answers one question across them. Setup, the
scripts and what each one does are in the cookbook's
README.md.
Run every command from the repo root.
Steps
Without credentials.json in the cookbook folder, the commands below run on a sample
workspace (the [setup] line says so) and answer about a fictional ceramics business; only
LLM_API_KEY is needed. Tell the user the answer is about sample data. Add --sample to
use the sample even when their account is set up. The sample lives in its own dataset,
google_workspace_memory_sample, and never mixes with the user's data.
- Run
uv run python examples/cookbooks/google_workspace_memory/google_workspace_memory.py --check.- Exit 0: go to step 2.
- Exit 2: each
[setup] MISSING:line names one fix. Don't create credentials yourself. Tell the user exactly which line to fix, using the README's "What it needs" table, and stop. If onlyGOOGLE_DRIVE_FOLDER_IDis missing, ask whether to run with--no-driveinstead.
- Run
uv run python examples/cookbooks/google_workspace_memory/google_workspace_memory.py. Add--ask "..."with the user's question if they asked one, and--no-calendar,--no-gmailor--no-drivefor any app they don't want used. The first run opens the browser once per app for consent; tell the user to approve each one. - The answer is everything after the line
[ask] Answer:. Give it to the user, and say which sources went in (the[ingest_calendar],[ingest_gmail]and[ingest_drive]lines).
If the user runs cognee as a server with their Google account connected there, add --api
to both commands: the server syncs and answers, and --check reports each app that is not
connected yet (the README's "Through a cognee server" section says how to connect it).
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.
- 7d ago First seen · 66 lines · 87 tokens per session scan A 2c2a0e3581e2
google-workspace-memory is a skill published in the GitHub repository topoteretes/cognee (33,094 stars, last pushed today), licensed Apache-2.0. It adds 87 tokens to every session and 902 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-30.
google-workspace-memory compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| google-workspace-memorytopoteretes/cognee | Skill | 33k | today | Apache-2.0 | A | 87 | Claude Code, Codex |
| openmemoryCaviraOSS/OpenMemory | Skill | 4.6k | 19d ago | Apache-2.0 | A | 96 | Claude Code, Codex |
| memseek-remembermemseekai/memseek | Skill | 11 | yesterday | Apache-2.0 | A | 24 | Claude Code |
| memseek-explainmemseekai/memseek | Skill | 11 | yesterday | Apache-2.0 | A | 25 | Claude Code |
| memseek-searchmemseekai/memseek | Skill | 11 | yesterday | Apache-2.0 | A | 22 | Claude Code |
| surface-learningsterrizoaguimor/celiums-memory | Skill | 23 | 2mo ago | Apache-2.0 | A | 60 | Claude Code |
| context-recoveryterrizoaguimor/celiums-memory | Skill | 23 | 2mo ago | Apache-2.0 | A | 37 | Claude Code |