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/benchmark-memorynpx skills add Abilityai/cornelius --skill benchmark-memorygit 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 | $0.00020 | $0.02377 |
| Opus 5 | $0.00010 | $0.01189 |
| Sonnet 5 | $0.00004 | $0.00475 |
| Haiku 4.5 | $0.00002 | $0.00238 |
Grade A, and why
benchmark-memory 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.
How it starts
The opening of the file, as written. The whole thing — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Benchmark Memory System
Systematic benchmarking framework to measure retrieval quality, compare configurations, and identify optimal parameters for the Local Brain Search memory system.
Purpose
- Measure retrieval quality objectively using LLM-as-judge scoring
- Compare different configuration settings (spreading vs static, parameter sweeps)
- Identify optimal parameters for different query types (factual, conceptual, synthesis)
- Generate reproducible results against frozen test datasets
Design Principles
- Contained: Skill + sub-agent + bundled scripts
- Reproducible: Test against frozen Brain snapshot
- Automated: LLM-as-judge for relevance scoring
- Analyzable: CSV output for analysis
State Dependencies
| Source | Location | Read | Write |
|---|---|---|---|
| Brain snapshot | .claude/skills/benchmark-memory/snapshots/ |
Yes | Yes |
| Query sets | .claude/skills/benchmark-memory/query-sets/ |
Yes | Yes |
| Benchmark results | .claude/skills/benchmark-memory/results/ |
Yes | Yes |
| Analysis reports | .claude/skills/benchmark-memory/analysis/ |
No | Yes |
| Memory system | resources/local-brain-search/ |
Yes | No |
Prerequisites
- Local Brain Search system indexed (
resources/local-brain-search/data/brain.faiss) - Python venv at
resources/local-brain-search/venv/with search dependencies - Claude Code CLI installed and authenticated (for LLM-as-judge scoring via headless mode)
LLM-as-Judge Scoring
This skill uses Claude Code headless mode (claude -p) for LLM relevance scoring, not a separate API key. This means:
- No
ANTHROPIC_API_KEYenvironment variable needed - Uses your existing Claude Code authentication
- Default model:
sonnet(good quality) - can also usehaiku(faster/cheaper) oropus - JSON output via prompt engineering for reliable scoring
To verify Claude Code is available:
claude --version
Installing Dependencies
Dependencies are installed in the local-brain-search venv:
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.
- 2d ago First seen · 309 lines · 20 tokens per session scan A ebe82eaedc86
benchmark-memory is a skill published in the GitHub repository Abilityai/cornelius (104 stars, last pushed 9d ago), licensed MIT. It adds 20 tokens to every session and 2,377 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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.