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 skills add Miaoge-Ge/coding-agent-skills --skill performance-expertgit clone --depth 1 https://github.com/Miaoge-Ge/coding-agent-skillsWrote 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/miaoge-ge/coding-agent-skills/performance-expert)<a href="https://agentmods.dev/skills/miaoge-ge/coding-agent-skills/performance-expert"><img src="https://agentmods.dev/badge/skills/miaoge-ge/coding-agent-skills/performance-expert/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/miaoge-ge/coding-agent-skills/performance-expert"><img src="https://agentmods.dev/badge/skills/miaoge-ge/coding-agent-skills/performance-expert.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00070 | $0.01056 |
| Opus 5.5 | $0.00028 | $0.00422 |
| Sonnet 5.5 | $0.00014 | $0.00211 |
| Haiku 4.5 | $0.00007 | $0.00106 |
Grade A, and why
performance-expert 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 1mo 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Optimization Expert
Measure, don't guess. Profile to find the real bottleneck, fix the biggest one, re-measure, repeat — and stop at the target. Algorithmic and I/O wins dwarf micro-optimizations.
When to Use
- Something is slow, memory-hungry, or doesn't scale.
- Profiling guidance for CPU, memory, I/O, or rendering.
- Setting/validating latency or throughput targets; benchmarking.
- Hunting a memory leak or GC pressure.
When NOT to Use
- Wrong output, not slow →
debugging-expert. - Behavior-preserving cleanup with no perf goal →
refactoring-expert. - DB query plans/indexing specifically →
sql-expert.
Core Principles
1. Measure first, always
- Profile before changing anything. Intuition about hotspots is usually wrong. Optimize the top item the profiler shows, not what you assume.
- Define the metric and target up front (p99 latency, throughput, peak memory, frame time) and a representative workload to measure against. Optimizing the wrong workload wastes effort.
- Beware micro-benchmarks that don't reflect production (warmup, caching, JIT, data size).
2. Biggest levers first
- Algorithmic complexity: O(n²)→O(n log n), removing redundant passes, and killing N+1 calls beat constant-factor tuning by orders of magnitude.
- Eliminate repeated work: cache/memoize pure results, precompute, hoist invariants out of loops, batch requests.
- Apply Amdahl's law: speeding up code that's 5% of runtime caps your win at 5%.
3. Levers by axis
- I/O-bound: batch + parallelize requests, add caching, cut round trips, stream instead of buffering, connection pooling.
- CPU-bound: better algorithm/data structures, reduce allocations in hot loops, vectorize/parallelize, avoid needless serialization.
- Memory: stream large data, fix leaks (lingering refs, unbounded caches, dangling listeners), right-size buffers, reduce per-object overhead.
- Frontend: shrink/split bundles, lazy-load, virtualize long lists, avoid layout thrash and unnecessary re-renders, debounce, use the browser cache/CDN.
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.
- 1mo ago First seen · 81 lines · 70 tokens per session scan A df29563aad2f
performance-expert is a skill published in the GitHub repository Miaoge-Ge/coding-agent-skills (7 stars, last pushed 4mo ago), licensed MIT. It adds 70 tokens to every session and 1,056 once invoked, about $0.0003 per session on Opus 5.5. 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
hotfix
Fixes an observed defect with reproducible evidence in one call: writes a short trace doc before touching code, implements the fix, and backs it with a regression test written before the fix. Production incidents are the motivating case, not a gate. When blocked, it halts by name and saves the doc for a later call to…
vibeflow-hotfix
Fixes an observed defect with reproducible evidence in one call: writes a short trace doc before touching code, implements the fix, and backs it with a regression test written before the fix. Use when a defect was observed and the evidence is in hand — an error message, a failing log, real data misbehaving — wherever…
diagnose-backend-bug
Diagnose a bounded backend or multi-service failure from GitHub Issues, Jira, Aone, user-provided exports, logs, traces, responses, stack traces, or job records. Use when a service, API, RPC, worker, queue, CLI, or scheduled job bug needs correlation through the project's existing observability route before repair; do…
prismer-python-debugpy
Debug Python: pdb REPL + debugpy remote (DAP).
debug-live
Guides root-cause investigations with debugging capabilities by setting breakpoints, starting a debug session, stepping through execution, inspecting variables, and tracing symptoms back to their origin. Prefer it for runtime bugs, failing tests, exceptions, crashes, hangs, wrong/null values, and unexpected output…
log-analyzer
A log-analysis helper that reads application and system logs to find unusual patterns and likely causes. Logs are records of events such as errors, requests, warnings, and service activity.