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.
npx agentmods add skills/abilityai/cornelius/insight-interviewnpx skills add Abilityai/cornelius --skill insight-interviewgit clone --depth 1 https://github.com/Abilityai/corneliusWhat 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 | $0.00052 | $0.01584 |
| Opus 5 | $0.00026 | $0.00792 |
| Sonnet 5 | $0.00010 | $0.00317 |
| Haiku 4.5 | $0.00005 | $0.00158 |
Grade A, and why
insight-interview 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 3d 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Insight Interview
A Socratic dialogue grounded in your own knowledge base. It finds what you already think, then probes the edges - gaps, underdeveloped claims, contradictions, missing connections - one question at a time. Your responses feed directly into the vault at the end.
Purpose
Not to summarize a topic. Not to explain research. To find out what you actually think - and make that thinking precise enough to live in the knowledge base.
The KB is the context, not the content. Every question is anchored in a note you already wrote.
State Dependencies
| Source | Location | Read | Write |
|---|---|---|---|
| Existing notes | Brain/ via Local Brain Search |
✓ | |
| Permanent notes | Brain/02-Permanent/ |
✓ | |
| Dialogue transcript | resources/insight-interview-[slug]-[date].md |
✓ | |
| Extracted insights | Brain/AI Extracted Notes/ |
✓ (via extract-insights) |
Process
Step 1: Search the KB
Run semantic search on the topic using Local Brain Search:
cd resources/local-brain-search && python search.py "[topic]" --top_k 15 --mode spreading
Also run a keyword grep across permanent notes:
grep -rl "[topic keywords]" Brain/02-Permanent/ Brain/AI\ Extracted\ Notes/ | head -20
Read the top 8-10 results. Understand:
- What the user already believes about this topic
- Which claims are well-developed vs. sketched
- Where tensions or contradictions exist between notes
- What connections are asserted but not fully argued
- What's notably absent (a gap where you'd expect a note)
Step 2: Map the Frontier
Before asking anything, internally map 5-7 candidate question zones:
- Existing claim to probe: A strong assertion in a note that could be sharpened or challenged
- Gap: An angle you'd expect him to have thought about but haven't found
- Contradiction: Two notes that pull in opposite directions
- Connection: A note that seems related to another topic he knows well - does he see it?
- So-what: A well-documented insight with no clear practical implication
- Origin: A belief stated as fact - where did it come from?
- Frontier: The newest or most uncertain note - what's unresolved?
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.
- 3d ago First seen · 178 lines · 52 tokens per session scan A 2b4e7911bb19
insight-interview is a skill published in the GitHub repository Abilityai/cornelius (104 stars, last pushed 10d ago), licensed MIT. It adds 52 tokens to every session and 1,584 once invoked, about $0.0003 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…