Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](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.svg" alt="Measured on agentmods" 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 | $0.00010 | $0.00183 |
| Sonnet 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 6d 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.
- 6d 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 5d ago), licensed MIT. It adds 21 tokens to every session and 367 once invoked, about $0.0001 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.
Other skills, from other repositories
agent-v3-memory-specialist
Agent skill for v3-memory-specialist - invoke with $agent-v3-memory-specialist.
Vizra ADK Memory System
Implement persistent memory, session context, and vector memory (RAG) for AI agents.
recall-ext
Develop and verify Recall's extension host, official extensions, manifests, and release wiring. Use for extension implementation or maintenance in this repository.
init-rag-rat
Use to set up rag-rat in a repository that is not indexed yet — when the rag-rat MCP server is DORMANT (its tools return {"status":"noindex"} with a "Run rag-rat init … then restart" remedy), or when the user asks to initialize / configure / "set up rag-rat" / "index this repo" / choose an embedding backend. Drives…
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.
internal-rag
Mandatory persistent project memory for substantial coding tasks. Use at task start, recovery, milestones, failures, before risky operations, before compaction, and before finishing. v1.0.1 adds type filtering, type-priority scoring, query expansion, grouped context output, and promote workflow.