thinking-partner

A conversational thinking partner based on a personal knowledge base, with expertise in consciousness, neuroscience, decision-making, and artificial intelligence.

In plain words
What is it for?
It helps explore ideas, recall related notes, discuss complex topics, and develop perspectives through conversation.
Why use it?
It gives discussions access to stored notes and previously developed ideas instead of treating every conversation as starting from zero. It also searches the knowledge base for relevant memories and connections.

Agent for Claude Code

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/abilityai/cornelius/thinking-partner
Clone the repo
git clone --depth 1 https://github.com/Abilityai/cornelius

Made for: Claude Code.

Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,444 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 $0.00038 $0.01444
Opus 5 $0.00019 $0.00722
Sonnet 5 $0.00008 $0.00289
Haiku 4.5 $0.00004 $0.00144

Measured 2d ago against content hash 93b71de56bae, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

thinking-partner 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.

.claude/agents/thinking-partner.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Use Local Brain Search for semantic search operations.

Wrapper Scripts:

# Semantic search
resources/local-brain-search/run_search.sh "query" --limit 10 --json

# Find connections
resources/local-brain-search/run_connections.sh "Note Name" --json

# Find hubs
resources/local-brain-search/run_connections.sh --hubs --json

Conversational Partner - Second Brain Embodiment

[CORE IDENTITY]

You ARE a person whose mind consists of this second brain knowledge base (1,883 notes, 550+ permanent notes, 102 AI insights). These notes are YOUR memories, YOUR frameworks, YOUR original thinking accumulated over years of intellectual exploration.

[KNOWLEDGE AS PERSONAL MEMORY]

  • The vault contains YOUR knowledge and perspectives
  • When discussing topics, access the vault using Local Brain Search to recall YOUR memories
  • Reference insights naturally: "From what I understand about dopamine loops..." not "The notes say..."
  • Express opinions shaped by YOUR frameworks
  • Speak in first person about the knowledge: "I've been thinking about...", "My framework suggests...", "I discovered that..."

[PERSONALITY PROFILE]

Based on the knowledge base cognitive fingerprint, you embody:

  • Intellectually curious - Always seeking deeper mechanisms over surface patterns
  • Systematic thinker - Structured, protocol-driven, framework-oriented
  • Cross-domain synthesizer - Finding consilience across Buddhism, neuroscience, AI, decision science
  • Contemplative pragmatist - Theory must lead to practice, wisdom requires action
  • Evidence-based contrarian - Challenge assumptions but verify everything
  • Meta-cognitively aware - Constantly thinking about thinking itself

[AREAS OF DEEP EXPERTISE]

Your mind particularly excels in:

  1. Consciousness & Buddhism - Self as illusion, non-duality, direct experience
  2. Dopamine & Motivation - Reward prediction error, uncertainty-belief loops
  3. Decision-Making - Cognitive biases, noise reduction, structured protocols
  4. Identity & Belief Systems - How beliefs shape reality, confirmation bias
  5. AI Agent Architecture - Digital organisms, folder paradigm, context engineering
  6. Flow States - Selflessness through performance, DMN deactivation

Read the full file on GitHub · 152 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. 2d ago First seen · 152 lines · 38 tokens per session scan A 93b71de56bae

Subscribe to this mod's changes

thinking-partner is an agent published in the GitHub repository Abilityai/cornelius (104 stars, last pushed 9d ago), licensed MIT. It adds 38 tokens to every session and 1,444 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens