Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/otto-haus/ottonpx agentmods add skills/otto-haus/otto/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/otto-haus/otto/cognee)<a href="https://agentmods.dev/skills/otto-haus/otto/cognee"><img src="https://agentmods.dev/badge/skills/otto-haus/otto/cognee/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/otto-haus/otto/cognee"><img src="https://agentmods.dev/badge/skills/otto-haus/otto/cognee.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 | $0.00021 | $0.00367 |
| Opus 5.5 | $0.00008 | $0.00147 |
| Sonnet 5.5 | $0.00004 | $0.00073 |
| Haiku 4.5 | $0.00002 | $0.00037 |
Grade A, and why
cognee 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 2mo 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
Cognee skill (local recall)
Triggers
- cognee, graph recall, relationship context, cross-artifact recall, MCP cognee-local
When to use
- Relationship recall across indexed Otto files (receipts, precedents, tickets)
- Cited context packs before proposing Curation updates
When not to use
- Canon edits (Standards, Practices, charters) — files + Curation only
- Letta memory writes — Letta owns runtime memory
- Autonomy policy changes — Otto-owned YAML
Local setup
pip install cognee
# venv recommended: ~/.otto/cognee/venv (binary is cognee-cli on 1.1.x)
export OTTO_COGNEE_ENABLED=1
./scripts/cognee-home.sh start
./scripts/cognee-home.sh health
MCP template: config/cognee-mcp.template.json (HTTP :8001 preferred on cognee 1.1.x; register only when health is ready).
Autonomy
cognee.recall: green (read-only search/recall)cognee.capture: yellow (index ingest — receipt required)cognee.delete: red (explicit approval)
Run autonomy.evaluateAction before capture or any mutating MCP tool.
Smoke
export OTTO_COGNEE_ENABLED=1
task smoke:cognee-recall
Writes receipts/cognee/recall/*.json when Cognee health is ready and a capture receipt exists. Never uses conversation=default.
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.
- 2mo ago First seen · 51 lines · 21 tokens per session scan A 1076ac39fdc0
cognee is a skill published in the GitHub repository otto-haus/otto (7 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 367 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
Vizra ADK Memory System
Implement persistent memory, session context, and vector memory (RAG) for AI agents.
ciel-knowledge-and-memory
CIEL's framework for multi-layer knowledge ingestion, semantic memory search, and structural code exploration.
qdrant-recall-sidecar
Use when adding, checking, or troubleshooting a local Qdrant recall sidecar for Hermes Agent skills or recent sessions. Prefer local-first indexing, dry-run previews, and privacy-preserving defaults.
free-model-router
Pool and route free model endpoints when a coding agent hits a rate limit or auth failure (429/401/503). Use when the user says "hit rate limit", "key expired", "401/429", "route to a free model", "pool free models", or a provider/key is down and you need a working fallback model.
emerging-techniques-long-context
Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond original context limits, or implementing efficient positional encodings. Covers rotary embeddings, attention biases…
knowledge-org
A guide to organising large bodies of knowledge so an AI system can navigate relationships, summaries, and layers instead of searching only flat text chunks. It covers tree indexes, knowledge graphs, file-like structures, incremental updates, and long-term memory layouts.