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/v0idos/performance-deity/optimizenpx skills add v0idOS/performance-deity --skill optimizegit clone --depth 1 https://github.com/v0idOS/performance-deityWhat 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 | $0.00034 | $0.00492 |
| Opus 5 | $0.00017 | $0.00246 |
| Sonnet 5 | $0.00007 | $0.00098 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
optimize 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
Execute all four phases in order. Do not skip any phase.
Phase 1 — Establish Baseline
- Identify the exact code to optimize.
- Run a micro-benchmark:
- Write a temporary micro-benchmark script in the user's workspace.
- The script MUST contain a warm-up phase (discard ≥10 iterations).
- The script MUST run ≥100 iterations and output the Average and P95 execution time.
- Run the script using the terminal.
- Delete the temporary script after recording the results.
- Note: If the script fails due to missing imports or dependencies, skip it and use the bash
timecommand as a fallback.
- Record P95 and Average. Do not proceed until the benchmark runs without error.
- Report baseline numbers before writing any new code.
Phase 2 — Algorithmic Analysis
- State the current Time Complexity (Big-O) explicitly.
- State the current Space Complexity and identify the primary allocation sites.
- Name the bottleneck precisely:
- "Nested loops causing O(n²) scaling"
- "Repeated string concatenation causing N heap allocations per call"
- "Full table scan caused by missing index on
user_id"
Phase 3 — Refactoring
- Rewrite using a more efficient algorithm or data structure (apply in priority order):
- Replace Array/List lookups with Hash Sets/Dictionaries: O(N) → O(1)
- Vectorization or batching instead of per-item iteration
- Caching/memoization of expensive pure computations
- Zero-allocation patterns and buffer reuse to reduce GC pressure
- Bitwise operations where mathematically equivalent
- Run the benchmark on the new code.
- If the new code is not measurably faster: discard it, select a different approach, repeat.
Phase 4 — Report
Present a Performance Report table:
| Metric | Baseline | Optimized | Δ |
|---|---|---|---|
| Average | Xms | Yms | -Z% |
| P95 | Xms | Yms | -Z% |
Follow with a one-paragraph explanation grounded in CPU/memory theory.
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 · 50 lines · 34 tokens per session scan A 770ca1afa7c0
optimize is a skill published in the GitHub repository v0idOS/performance-deity (2 stars, last pushed 4mo ago), licensed MIT. It adds 34 tokens to every session and 492 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
agent-evaluation-reporting
Use when summarizing agent evaluations where autonomous, assisted, failed, timed-out, or invalid outcomes must remain distinct and comparable.
nemo-evaluator-sdk
Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.
evaluating-code-models
Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.
evaluating-llms-harness
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.
Gene Panel Selection Workflow
End-to-end workflow for gene panel design in scRNA-seq and spatial transcriptomics, that should be STRICTLY followed: dataset understanding + smart downsampling + train/test splits, algorithmic selection (HVG/DE/RF/scGeneFit/SpaPROS), optimal sub-panel discovery (ARI vs size), biological completion with a stability…
benchmark-radar
Find, inspect, and check AI benchmark records with the Benchmark Radar CLI. Use when a request needs benchmark discovery, details, recent Radar evidence, or local data health; do not assume why the user needs the results.