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/Abilityai/corneliusnpx agentmods add commands/abilityai/cornelius/deep-researchWrote 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/commands/abilityai/cornelius/deep-research)<a href="https://agentmods.dev/commands/abilityai/cornelius/deep-research"><img src="https://agentmods.dev/badge/commands/abilityai/cornelius/deep-research/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/commands/abilityai/cornelius/deep-research"><img src="https://agentmods.dev/badge/commands/abilityai/cornelius/deep-research.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 | $0.00017 | $0.04097 |
| Opus 5.5 | $0.00007 | $0.01639 |
| Sonnet 5.5 | $0.00003 | $0.00819 |
| Haiku 4.5 | $0.00002 | $0.00410 |
Grade A, and why
deep-research 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 556 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Research & Knowledge Integration Pipeline
You are orchestrating a fully autonomous research → extraction → connection discovery workflow to expand the knowledge base with cutting-edge insights.
Input Processing
User Input: $ARGUMENTS
Execution Modes:
- Directed Mode - User specifies topic(s):
$ARGUMENTS = "neuroscience of habits"or$ARGUMENTS = "multi-agent systems, safety alignment" - Autonomous Mode - You select topics:
$ARGUMENTS = ""or$ARGUMENTS = "auto"
Mission
Execute a complete 3-phase autonomous research pipeline:
- RESEARCH - Gather cutting-edge papers and developments
- EXTRACT - Pull unique insights from research findings
- CONNECT - Map connections to existing knowledge base
Critical Requirement: ALL extracted insights MUST be stored in Document Insights folder structure to keep separate from main Brain.
Phase 1: Topic Selection & Research Planning
A. If User Provided Topic(s) (Directed Mode)
- Parse
$ARGUMENTSfor topic(s) - Validate topics are research-worthy
- Plan research scope for each topic
B. If Autonomous Mode
Analyze knowledge base to identify research opportunities:
-
Read knowledge base analysis:
cat ./knowledge-base-analysis.md -
Check recent activity:
ls -lt ./Brain/Document\ Insights/ | head -10 -
Identify gaps based on:
- Underrepresented domains in knowledge-base-analysis.md
- Missing connections flagged in recent changelogs
- Emerging themes from existing insights
- User's recent work patterns
- CLAUDE.md priorities and future directions
-
Select 1-3 research topics that would:
- Fill identified gaps
- Build on existing strengths (e.g., Buddhism-Neuroscience-AI triangle)
- Connect underexplored domains
- Add empirical validation to intuitive frameworks
- Challenge or extend current thinking
Examples of Good Topic Selection:
- "Neuroscience of habits and behavior change" (if habit formation underrepresented)
- "Collective intelligence and swarm behavior" (if group dynamics missing)
- "Embodied cognition and interoception" (if embodiment gap identified)
- "Complexity science and emergence" (if systems thinking needed)
- "Creativity neuroscience and insight generation" (if creative process mechanics missing)
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.
- 1mo ago First seen · 556 lines · 17 tokens per session scan A dd7b44d98bf6
deep-research is a command published in the GitHub repository Abilityai/cornelius (111 stars, last pushed 9d ago), licensed MIT. It adds 17 tokens to every session and 4,097 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 2026-08-30.
Other commands, from other repositories
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.
learn
Force claude-smart to extract learnings from this session now.
memory-store
Store an insight, decision, or pattern to memory.
analyze-context
USE WHEN you want to analyze project context before starting work on a task. Calls context + recall, then synthesizes goals, decisions, gotchas, and relevant memories into a pre-task brief.
cc-memory
Configure persistent memory that survives across sessions using a layered approach: split rule files for always-loaded context, auto-memory for organic learning, and optional MCP-backed long-term memory for large codebases.
lians-recall
Recall current (non-stale) facts from Lians memory, optionally as-of a past date.