oms-cognee

oms-cognee is a skill for Claude Code, Codex from armelhbobdad/oh-my-skills. It costs 220 tokens per session (4,176 once invoked), scanned A, original, Apache-2.0.

A Python engine for giving AI agents persistent memory built from source text, files, or web addresses. It combines semantic search with a knowledge graph of entities and relationships, while keeping source information about where facts came from.

In plain words
What is it for?
It helps import data, build a searchable knowledge graph, and query it using different search styles, including graph-based answers, text chunks, summaries, and time-aware searches. Its main workflow is to add data, build the memory, and search it.
Why use it?
It lets an agent search information that remains available after the current conversation instead of relying only on its short-term context. The linked entities and source records can make results easier to connect and trace.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions AGENTS.md.

Good fit It helps import data, build a searchable knowledge graph, and query it using different search styles, including graph-based answers, text chunks, summaries, and time-aware searches. Its main workflow is to add data, build the memory, and search it.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/armelhbobdad/oh-my-skills/oms-cognee
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add armelhbobdad/oh-my-skills --skill oms-cognee
Clone the repo
git clone --depth 1 https://github.com/armelhbobdad/oh-my-skills

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 oms-cognee

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

agentmods 80×15 button for oms-cognee

Your own site · 80×15
<a href="https://agentmods.dev/skills/armelhbobdad/oh-my-skills/oms-cognee"><img src="https://agentmods.dev/badge/skills/armelhbobdad/oh-my-skills/oms-cognee.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 220 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,176 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00220 $0.04176
Opus 5 $0.00110 $0.02088
Sonnet 5 $0.00044 $0.00835
Haiku 4.5 $0.00022 $0.00418

Measured 12d ago against content hash fcfbbf8239a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

oms-cognee scanned grade A with 1 finding 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 12d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- **`cognee.start_ui` is sync (not async) and requires a `pid_callback` positional argument.** Do not call `await cognee.start_ui()` — the function returns `Optional[subprocess.Popen]` synchronously. Signature: `start_ui
skills/oms-cognee/0.5.8/oms-cognee/SKILL.md · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.

oms-cognee

Overview

Cognee is an open-source knowledge-graph memory engine for AI agents. It combines a vector store (semantic search), a graph store (entities + relationships), and a relational store (provenance) into a single three-layer memory architecture. The canonical workflow is add → cognify → search: ingest data, build a knowledge graph, then query it.

  • Source: topoteretes/cognee @ v0.5.8 (commit b51dcce) [SRC:pyproject.toml:L4]
  • Language: Python >=3.10, <3.14 [SRC:pyproject.toml:L10]
  • Forge tier: Deep (AST + ccc + QMD + docs fetch)
  • Public exports: 25 top-level names in cognee/__init__.py [AST:cognee/__init__.py:L1]
  • Confidence: All T1 (AST-verified from source clone)
  • Async model: Cognee is async-first — nearly all top-level functions are coroutines and must be awaited [EXT:https://docs.cognee.ai/getting-started/quickstart]

Quick Start

import asyncio
import cognee
from cognee import SearchType

async def main():
    # (optional) start from a clean slate
    await cognee.prune.prune_data()
    await cognee.prune.prune_system(metadata=True)

    # 1) Ingest data — text, file path, URL, or list of any of those
    await cognee.add(
        "Cognee turns documents into AI memory.",
        dataset_name="main_dataset",
    )

    # 2) Build the knowledge graph
    await cognee.cognify(datasets="main_dataset")

    # 3) Query the graph with graph-backed LLM completion (default)
    results = await cognee.search(
        query_text="What does Cognee do?",
        query_type=SearchType.GRAPH_COMPLETION,
    )
    for r in results:
        print(r)

if __name__ == "__main__":
    asyncio.run(main())

Signatures: [AST:cognee/api/v1/add/add.py:L21] · [AST:cognee/api/v1/cognify/cognify.py:L44] · [AST:cognee/api/v1/search/search.py:L27]

Before running, set LLM_API_KEY for graph extraction and completion; Cognee defaults to OpenAI but supports litellm-compatible providers (Anthropic, Gemini, Ollama, etc.) via cognee.config.set_llm_provider(...) and friends. [AST:cognee/api/v1/config/config.py:L141] · [SRC:cognee/api/v1/add/add.py:L166]

Read the full file on GitHub · 194 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 12d ago First seen · 194 lines · 220 tokens per session scan A fcfbbf8239a7

Subscribe to this mod's changes

oms-cognee is a skill published in the GitHub repository armelhbobdad/oh-my-skills (7 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 220 tokens to every session and 4,176 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.