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/minihellboy/factorminer/factor-benchmarknpx skills add minihellboy/factorminer --skill factor-benchmarkgit clone --depth 1 https://github.com/minihellboy/factorminerWhat 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 | $0.00079 | $0.00517 |
| Opus 5 | $0.00039 | $0.00259 |
| Sonnet 5 | $0.00016 | $0.00103 |
| Haiku 4.5 | $0.00008 | $0.00052 |
Grade A, and why
factor-benchmark 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.
What it actually says
Factor Benchmark
This skill runs FactorMiner's canonical benchmark surface — the rigorous comparison layer that turns a single run into evidence.
Modes
| Mode | What it answers |
|---|---|
table1 |
Top-K freeze benchmark across configured universes vs. baselines — the headline reproduction. |
ablation-memory |
How much does experience memory contribute? |
ablation-strategy |
Effect of memory policy × dependence metric × backend. |
cost-pressure |
How does the library hold up under rising transaction costs? |
efficiency |
Operator- and factor-level runtime/compute cost. |
suite |
The full benchmark suite in one run. |
Workflow
Run a benchmark
factorminer -o output/bench benchmark table1 --data path/to/market_data.csv
factorminer -o output/bench benchmark suite --data path/to/market_data.csv
Pass a pre-mined library to benchmark a specific run rather than mining fresh:
factorminer -o output/bench benchmark table1 \
--data market_data.csv \
--factor-miner-library output/run1/factor_library.json
efficiency takes no data — it profiles the engine itself.
Read the result
The CLI prints a per-universe summary (library IC, ICIR, avg |ρ|) and writes JSON payloads into the output directory. Fold those JSON files into the research note with factor-report --benchmark.
Interpreting ablations
- An ablation that removes a feature and barely moves the metric means that feature is not earning its compute on this dataset — report that plainly.
cost-pressureis the honesty check: a library that only wins at zero cost is not a result.
Guardrails
- Benchmark numbers are comparative research evidence, not a performance guarantee.
- Use the same dataset and splits across compared runs, or the comparison is meaningless.
- Reproduction claims must cite the exact config and run directory.
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 · 57 lines · 79 tokens per session scan A c5b78a8da140
factor-benchmark is a skill published in the GitHub repository minihellboy/factorminer (105 stars, last pushed 16d ago), licensed MIT. It adds 79 tokens to every session and 517 once invoked, about $0.0004 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.