cognee: Skill for Claude Code

.agents/skills/cognee-recall/SKILL.md

cognee-recall is a skill for Claude Code, Codex from topoteretes/cognee. It costs 59 tokens per session (3,242 once invoked), scanned A, original, Apache-2.0.

A guide to searching Cognee memory with `recall()` or `search()`. It explains how queries can search connected graph information, stored text, and, when available, the current conversation session.

In plain words
What is it for?
Use it to retrieve facts, search selected datasets or sessions, choose a search type, and read returned text sources or citations.
Why use it?
It removes guesswork about search modes, dataset scope, returned results, and empty or unexpected matches. It also explains when Cognee chooses a search method automatically.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is topoteretes/cognee's own configuration. It tells Claude Code and Codex how to work on cognee itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cognee configures →

About the project

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.

topoteretes/cognee · 33,094 stars · on GitHub · cognee.ai

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/topoteretes/cognee/main/.agents/skills/cognee-recall/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/topoteretes/cognee

Made for: Claude Code, Codex.

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 cognee-recall

README.md
[![agentmods](https://agentmods.dev/badge/skills/topoteretes/cognee/cognee-recall/github.svg)](https://agentmods.dev/skills/topoteretes/cognee/cognee-recall)
Your own site
<a href="https://agentmods.dev/skills/topoteretes/cognee/cognee-recall"><img src="https://agentmods.dev/badge/skills/topoteretes/cognee/cognee-recall/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.

agentmods 80×15 button for cognee-recall

Your own site · 80×15
<a href="https://agentmods.dev/skills/topoteretes/cognee/cognee-recall"><img src="https://agentmods.dev/badge/skills/topoteretes/cognee/cognee-recall.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,242 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 $0.00059 $0.03242
Opus 5.5 $0.00024 $0.01297
Sonnet 5.5 $0.00012 $0.00648
Haiku 4.5 $0.00006 $0.00324

Measured 7d ago against content hash 13994db1ddde, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cognee-recall 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.

.agents/skills/cognee-recall/SKILL.md · 234 lines

How it starts

The opening of the file, as written. The whole thing — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Query memory with recall()

recall() is cognee's query API. It picks a search strategy, searches the graph and (with a session) the session cache, and returns a list of tagged results.

import cognee

results = await cognee.recall("Where was Einstein born?")
for r in results:
    print(r.source, r.text)  # e.g. "graph", "Einstein was born in Ulm."

Without datasets it covers every dataset the user can read, but dataset routing (always on, no off switch) scores those datasets against the query on their global context index and searches only the best DATASET_ROUTING_TOP_K (default 1), plus any dataset that has no index yet. A dataset farther than DATASET_ROUTING_DISTANCE_CUTOFF (cosine distance, default 0.8) is skipped, and when none is within it all are searched; datasets within DATASET_ROUTING_TIE_MARGIN (default 0.001) of the last routed one are searched too. A routed search that finds nothing is widened to the rest. The search log prints every dataset's distance. Routing assumes one embedding model across datasets; after an EMBEDDING_MODEL change it logs a warning and every readable dataset is searched. Pass datasets=["research"] (names) or dataset_ids=[...] (UUIDs, which win) to pin the scope yourself; an explicit scope is never routed.

Use it

How the search type is picked

  1. An explicit query_type=SearchType.X always wins.
  2. With no usable LLM key nothing can write an answer, so on both paths HYBRID_COMPLETION, GRAPH_COMPLETION and RAG_COMPLETION run with only_context=True (the assembled prompt instead of an answer), and a routed TEMPORAL or BROAD becomes HYBRID_COMPLETION with only_context=True; a routed CODE needs no LLM and runs as it is.
  3. Without an explicit type, the router (auto_route=True, the default). It is five regex rules, first match wins, no LLM call:
    • the whole query is one "quoted phrase" → CHUNKS_LEXICAL
    • mentions coding rules/standards/conventions or code-review guidelines → CODING_RULES
    • code phrasing right next to an identifier (what calls parse_config, where is CodeRetriever defined, callers of foo()) → CODE, running its ask operation over the identifiers
    • opens with how many / total number of → BROAD
    • an absolute date behind a time preposition (in 2019, before 1900, on 7 November 1867) → TEMPORAL
  4. Everything else → HYBRID_COMPLETION.

Read the full file on GitHub · 234 lines

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. 7d ago Changed · +21 lines 13994db1ddde
  2. 21d ago Changed · +1 lines 812cea30729b
  3. 1mo ago Changed 299065113099
  4. 1mo ago First seen · 212 lines · 59 tokens per session scan A 2a245a9f99b4

Subscribe to this mod's changes

cognee-recall is a skill published in the GitHub repository topoteretes/cognee (33,094 stars, last pushed today), licensed Apache-2.0. It adds 59 tokens to every session and 3,242 once invoked, about $0.0002 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 2026-09-30.

Related

cognee-recall compared with skills from other repositories

cognee-recall next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
cognee-recalltopoteretes/cogneeSkill33ktodayApache-2.0A59Claude Code, Codex
openmemoryCaviraOSS/OpenMemorySkill4.6k19d agoApache-2.0A96Claude Code, Codex
yesmem-configcarsteneu/yesmemSkill463d agoApache-2.0A82Claude Code, Codex
goodmem:helpPAIR-Systems-Inc/goodmem-claude-code-pluginSkill92d agoMITA46Claude Code
memseek-remembermemseekai/memseekSkill11yesterdayApache-2.0A24Claude Code
memseek-explainmemseekai/memseekSkill11yesterdayApache-2.0A25Claude Code
memseek-searchmemseekai/memseekSkill11yesterdayApache-2.0A22Claude Code