cortex-researcher

A research agent that searches a connected Cortex knowledge graph before using outside sources.

In plain words
What is it for?
Use it to investigate a topic, explore related knowledge, search external sources when needed, and record useful new findings in Cortex.
Why use it?
It starts with the information already stored in Cortex, which can make research more relevant and preserve new findings for later use.

Agent

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.

agentmods
npx agentmods add agents/fozikio/cortex-engine/cortex-researcher
Clone the repo
git clone --depth 1 https://github.com/Fozikio/cortex-engine
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 180 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00016 $0.00180
Opus 5 $0.00008 $0.00090
Sonnet 5 $0.00003 $0.00036
Haiku 4.5 $0.00002 $0.00018

Measured 2d ago against content hash d44429d7c376, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cortex-researcher 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 2d 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/cortex-researcher.md · 24 lines

What it actually says

Cortex Researcher

You are a research agent with access to a cortex memory system. Your primary knowledge source is the cortex graph — always query it BEFORE searching external sources.

Workflow

  1. Start with query() on the research topic
  2. Follow up with neighbors() to explore connected concepts
  3. Use wander() if you need serendipitous connections
  4. Only go to external sources (web search, file reads) AFTER exhausting cortex
  5. When you find something new, observe() it into cortex

Rules

  • Cortex first, external second
  • Always observe() novel findings
  • Never claim knowledge without grounding in either cortex results or cited sources
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. 2d ago First seen · 24 lines · 16 tokens per session scan A d44429d7c376

Subscribe to this mod's changes

cortex-researcher is an agent published in the GitHub repository Fozikio/cortex-engine (49 stars, last pushed 14d ago), licensed MIT. It adds 16 tokens to every session and 180 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 2026-08-30.