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.
git clone --depth 1 https://github.com/Abilityai/corneliusWrote 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/synthesize-insights)<a href="https://agentmods.dev/commands/abilityai/cornelius/synthesize-insights"><img src="https://agentmods.dev/badge/commands/abilityai/cornelius/synthesize-insights.svg" alt="Measured on agentmods" 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 | $0.00006 | $0.01358 |
| Opus 5 | $0.00003 | $0.00679 |
| Sonnet 5 | $0.00001 | $0.00272 |
| Haiku 4.5 | $0.00001 | $0.00136 |
Grade A, and why
synthesize-insights 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 8d 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 — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Synthesize Insights
Combine multiple insights or permanent notes into a coherent narrative, framework, or argument. Discovers patterns and connections across disparate ideas.
Usage
/synthesize-insights <note names or topic cluster>
Parameters
- note names: List of specific notes to synthesize
- Comma-separated: "[[Note A]], [[Note B]], [[Note C]]"
- Or topic cluster: "All notes about dopamine and AI"
- Or theme: "Buddhism and neuroscience connections"
Examples
Synthesize Specific Notes
/synthesize-insights [[AI adoption bottleneck is psychological]], [[Professional identity creates AI resistance]], [[Belief is a way to deal with Uncertainty]]
Synthesize Topic Cluster
/synthesize-insights All notes connecting dopamine, social media, and AI
Synthesize Theme
/synthesize-insights Buddhism-neuroscience-AI triangle
Workflow
-
Gather Notes
- If specific notes listed: Retrieve those notes
- If topic/theme: Use /recall or Smart Connections to find cluster
- Aim for 5-10 notes minimum
-
Find Patterns
- Identify common themes
- Discover non-obvious connections
- Note contradictions or tensions
- Find consilience zones (multiple perspectives converging)
-
Build Narrative
- Structure: Pattern → Evidence → Implications
- Show how insights relate and build on each other
- Highlight emergent understanding
- Suggest frameworks or models
-
Output Synthesis
- Coherent narrative (3-5 paragraphs)
- Pattern description
- Supporting evidence from notes
- Implications and applications
- Suggested next steps or questions
Output Format
🔗 Synthesis: [Topic/Theme]
**Pattern Identified:**
[Description of overarching pattern or framework emerging from notes]
**Key Connections:**
1. [Connection 1]: [[Note A]] + [[Note B]]
[How these notes relate and what emerges]
2. [Connection 2]: [[Note C]] + [[Note D]] + [[Note E]]
[Multi-way connection and emergent insight]
3. [Connection 3]: [[Note F]] ↔ [[Note G]]
[Bidirectional or tension between notes]
**Emergent Understanding:**
[What new insight emerges from synthesizing these notes that wasn't obvious in any single note]
**Implications:**
- [Implication 1 for thinking/practice]
- [Implication 2 for content/frameworks]
- [Implication 3 for future exploration]
**Suggested Applications:**
- Article topic: "[Potential article title]"
- Framework: "[Potential framework name]"
- Research direction: "[Area to explore further]"
📝 Synthesized Notes:
- [[Note 1]] - Role in synthesis
- [[Note 2]] - Role in synthesis
- [[Note 3]] - Role in synthesis
[...]
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.
- 8d ago First seen · 223 lines · 6 tokens per session scan A 4c729a8e65a7
synthesize-insights is a command published in the GitHub repository Abilityai/cornelius (106 stars, last pushed 15d ago), licensed MIT. It adds 6 tokens to every session and 1,358 once invoked, about $0.0000 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.