Borrowing it
Nothing to install: this file belongs to adrienm7/ergopti. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/adrienm7/ergopti/main/.agents/skills/perf-profiling/SKILL.mdgit clone --depth 1 https://github.com/adrienm7/ergoptiWrote 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/adrienm7/ergopti/perf-profiling)<a href="https://agentmods.dev/skills/adrienm7/ergopti/perf-profiling"><img src="https://agentmods.dev/badge/skills/adrienm7/ergopti/perf-profiling/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/adrienm7/ergopti/perf-profiling"><img src="https://agentmods.dev/badge/skills/adrienm7/ergopti/perf-profiling.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 | $0.00053 | $0.00402 |
| Opus 5.5 | $0.00021 | $0.00161 |
| Sonnet 5.5 | $0.00011 | $0.00080 |
| Haiku 4.5 | $0.00005 | $0.00040 |
Grade A, and why
perf-profiling 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 15d 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
Performance profiling
Do not optimize from intuition. Establish a reproducible baseline, label every number's provenance, change one mechanism, and repeat the same measurement. Complexity or operation counts are useful hypotheses; they are not measured latency.
Read only the scope reference that matches the request:
- Windows/AutoHotkey: references/ahk.md
- macOS/Hammerspoon: references/hammerspoon.md
Before proposing a cache or architectural shortcut, read
docs/memory/README.md and the relevant topic plus
docs/memory/rejected_proposals.md. A cache is an optimization only when its
invalidation contract is proved.
Shared method
- Resolve the real runtime log directory before asserting that evidence exists or is absent. A log filename records process start; date events from their line timestamps.
- Record the time window, input/workload, machine state, sample count, and command or script used. Report tail behavior and maximum, not mean alone.
- Trace the highest-frequency path and count allocations, lookups, I/O, native calls, and work repeated with an unchanged result.
- Prefer removing unnecessary work to adding a cache. Do not trade an ordering, ownership, suspension, privacy, or output guarantee for speed.
- Measure after with the same method and run every gate selected by
verify-change.
An audit reports proposed changes; it does not edit production code unless the user explicitly asks for implementation. Never weaken a test to obtain a green performance change, and never push without current authorization.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 15d ago First seen · 40 lines · 53 tokens per session scan A ee97447a3c73
perf-profiling is a skill published in the GitHub repository adrienm7/ergopti (14 stars, last pushed today), licensed MIT. It adds 53 tokens to every session and 402 once invoked, about $0.0002 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 2026-10-14.
Other skills, from other repositories
bloat-detector
Detects codebase bloat via dead code, duplication, complexity, and doc bloat scans. Use when codebase feels large or before a release.
fix-ci
Fix CI failures and performance regressions for a Julia package PR by iterating - triage the latest CI results, fix one root cause, verify locally, push. Use when a PR's GitHub Actions or Buildkite CI is failing, or when CI jobs run slower than they do on the main branch. Verifies CPU and GPU compilation locally…
performance-analysis
Performance analysis, bottleneck detection, and optimization recommendations. Use when profiling slow code or systems, hunting a performance regression, or producing an optimization plan with measurable targets.
performance-optimizer
Analyze and optimize code performance, identify bottlenecks, and suggest improvements.
performance-optimization
Use when performance requirements exist, profiling reveals bottlenecks, or Core Web Vitals need improvement. Do NOT use without evidence — premature optimization adds complexity.
performance-analysis
Comprehensive performance analysis, bottleneck detection, and optimization recommendations for Claude Flow swarms.