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/auto-discoverynpx skills add Abilityai/cornelius --skill auto-discoverygit 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/skills/abilityai/cornelius/auto-discovery)<a href="https://agentmods.dev/skills/abilityai/cornelius/auto-discovery"><img src="https://agentmods.dev/badge/skills/abilityai/cornelius/auto-discovery.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 | $0.00017 | $0.01297 |
| Opus 5 | $0.00009 | $0.00648 |
| Sonnet 5 | $0.00003 | $0.00259 |
| Haiku 4.5 | $0.00002 | $0.00130 |
Grade A, and why
auto-discovery 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 4d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auto-Discovery
Autonomous cross-domain connection hunter. Samples notes from different thematic clusters and finds meaningful relationships that semantic similarity alone would miss.
Purpose
Find non-obvious, cross-domain connections - notes with low semantic similarity (0.50-0.70) but high conceptual strength. These are the hidden patterns in the knowledge base.
State Dependencies
| Source | Location | Read | Write | Description |
|---|---|---|---|---|
| Permanent Notes | Brain/02-Permanent/ |
✓ | Sampling source | |
| AI Extracted Notes | Brain/AI Extracted Notes/ |
✓ | Sampling source | |
| Document Insights | Brain/Document Insights/ |
✓ | Sampling source | |
| Local Brain Search | resources/local-brain-search/ |
✓ | Similarity scores, connections | |
| Session Changelogs | Brain/05-Meta/Changelogs/ |
✓ | Dated discovery log | |
| Master Changelog | Brain/CHANGELOG.md |
✓ | ✓ | Summary entry |
Prerequisites
- Local Brain Search index up-to-date (
/refresh-index) - Brain vault accessible
Process
Step 1: Get Current Date
date '+%Y-%m-%d'
Use for changelog filename.
Step 2: Strategic Sampling
Sample from 3-5 diverse domains using Local Brain Search:
# --no-track: autonomous weekly loop; its cross-domain samples must NOT train q-values (scope-primitive learning hygiene).
# BRAIN_READ_SCOPE=<wide>: cross-domain (non-core) sampling is this skill's PURPOSE, so it must read past
# the core fingerprint. Set it wide rather than letting it fail closed to core once enforcement is on.
# Only the learn axis is closed (--no-track); the read axis is deliberately wide.
BRAIN_READ_SCOPE=core,Books,document-insights,meta,inbox,output resources/local-brain-search/run_search.sh "dopamine" --limit 5 --no-track --json
BRAIN_READ_SCOPE=core,Books,document-insights,meta,inbox,output resources/local-brain-search/run_search.sh "uncertainty" --limit 5 --no-track --json
BRAIN_READ_SCOPE=core,Books,document-insights,meta,inbox,output resources/local-brain-search/run_search.sh "identity" --limit 5 --no-track --json
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.
- 4d ago First seen · 165 lines · 17 tokens per session scan A a8f378e8d9f7
auto-discovery is a skill published in the GitHub repository Abilityai/cornelius (105 stars, last pushed 11d ago), licensed MIT. It adds 17 tokens to every session and 1,297 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.
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…