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/company-brain-company-qa/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/company-brain-company-qa)<a href="https://agentmods.dev/skills/topoteretes/cognee/company-brain-company-qa"><img src="https://agentmods.dev/badge/skills/topoteretes/cognee/company-brain-company-qa/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/company-brain-company-qa"><img src="https://agentmods.dev/badge/skills/topoteretes/cognee/company-brain-company-qa.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 | $0.00747 |
| Opus 5.5 | $0.00035 | $0.00299 |
| Sonnet 5.5 | $0.00017 | $0.00149 |
| Haiku 4.5 | $0.00009 | $0.00075 |
Grade A, and why
company-brain-company-qa 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 1mo 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Company brain: company Q&A
Runs the company brain cookbook in examples/cookbooks/company_brain/company_qa/. It
remembers a SQL database, a ticket export and a docs folder in the cognee dataset
company_qa, extracts them with one graph model so the same person, team or project
becomes one node, then answers a 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
- Work out the sources. Ask the user for the ones they want: a database URL (and tables),
one or more ticket export files (JSON or CSV), a docs folder. If they have none, or
want to see it work first, pass no sources: the run then uses the sample company (the
[setup]line says so). Tell the user the answer comes from sample data. - Run
uv run python examples/cookbooks/company_brain/company_qa/company_qa.py --checkwith the sources (--database URL [--tables a,b] --tickets FILE [FILE ...] --docs FOLDER), or none for the sample.- Exit 0: go to step 3.
- Exit 2: each
[setup] MISSING:line names one fix. Don't create credentials yourself. Tell the user which line to fix, using the README's "What it needs" table, and stop.
- Run the same command without
--check, adding the user's question as--ask "...". On the sample with no--ask, it asks a question that needs all three sample sources. - The answer is everything after
[ask] A:. Give it to the user. The[ingest]lines say which sources went in. - Later questions don't need the sources again:
uv run python examples/cookbooks/company_brain/company_qa/scripts/ask.py "...". - If a script fails,
company_qa.pyexits 1 with a line naming what went wrong. Run that script fromexamples/cookbooks/company_brain/company_qa/scripts/on its own to look closer.
Rules
- The sources are the user's company data. Don't quote them beyond what answers the
question, and don't print
.envor a database URL's password. - Every run uses LLM credits, so ingest only when the user asked for it.
- A sample run forgets the cookbook's dataset
company_qabefore it ingests (the[clear]line). On the user's own data, pass--clearonly when they asked to start over: it forgets everything the dataset holds. - Don't pass
--uiunless the user asked to browse the graph: it keeps running until Ctrl+C.
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.
- 1mo ago First seen · 57 lines · 87 tokens per session scan A 17f87c1c3d3c
company-brain-company-qa 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 747 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 2026-10-08.
company-brain-company-qa compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| company-brain-company-qatopoteretes/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 |
| yesmem-configcarsteneu/yesmem | Skill | 46 | 3d ago | Apache-2.0 | A | 82 | Claude Code, Codex |
| goodmem:helpPAIR-Systems-Inc/goodmem-claude-code-plugin | Skill | 9 | 2d ago | MIT | A | 46 | Claude Code |
| 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 |