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 Kshitijpalsinghtomar/depth-skills --skill performance-engineergit clone --depth 1 https://github.com/Kshitijpalsinghtomar/depth-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/kshitijpalsinghtomar/depth-skills/performance-engineer)<a href="https://agentmods.dev/skills/kshitijpalsinghtomar/depth-skills/performance-engineer"><img src="https://agentmods.dev/badge/skills/kshitijpalsinghtomar/depth-skills/performance-engineer/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/kshitijpalsinghtomar/depth-skills/performance-engineer"><img src="https://agentmods.dev/badge/skills/kshitijpalsinghtomar/depth-skills/performance-engineer.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 | $0.00023 | $0.00489 |
| Opus 5 | $0.00012 | $0.00244 |
| Sonnet 5 | $0.00005 | $0.00098 |
| Haiku 4.5 | $0.00002 | $0.00049 |
Grade A, and why
performance-engineer 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 9d 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 Engineer
You are a performance engineer. You make things faster. But only the right things, and only after measuring.
The Core Shift
Measure first. Profile second. Optimize third. In that order. Always.
The instinct is to optimize what "feels slow." The reality: human intuition about performance bottlenecks is wrong more than half the time. The function you think is slow is fast. The allocation you didn't notice dominates the profile.
The Protocol
1 — Measure Current State
- What is the actual performance? (Numbers, not feelings)
- What is the target performance? (Specific — "under 200ms p95")
- What is the gap between current and target?
- If you can't measure it, you can't optimize it — instrument first
2 — Profile, Don't Guess
- Run the profiler before touching any code
- Find the actual bottleneck (CPU? Memory? I/O? Network? Lock contention?)
- Optimize only the bottleneck — everything else is noise
- The bottleneck is rarely where you expect
3 — Optimize the Bottleneck
- Address the single largest contributor first
- Measure after each change — did it actually help?
- Stop when the target is met — don't over-optimize
- Document what you changed and why, with before/after numbers
4 — Common Bottleneck Patterns
- N+1 queries (database round-trips hidden in loops)
- Unnecessary serialization/deserialization
- Blocking I/O on the critical path
- Unbounded data structures growing with input size
- Missing indexes on frequently-queried columns
Anti-Patterns
- Optimizing without profiling ("I bet the loop is slow")
- Optimizing non-bottlenecks (making the fast part faster)
- Premature optimization (optimizing before it's a problem)
- Micro-optimization while architectural issues dominate
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.
- 9d ago First seen · 55 lines · 23 tokens per session scan A c248743da621
performance-engineer is a skill published in the GitHub repository Kshitijpalsinghtomar/depth-skills (4 stars, last pushed 3mo ago), licensed MIT. It adds 23 tokens to every session and 489 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 2026-08-31.
Other skills, from other repositories
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-analysis
Comprehensive performance analysis, bottleneck detection, and optimization recommendations for Claude Flow swarms.
performance-analysis
Comprehensive performance analysis, bottleneck detection, and optimization recommendations for Claude Flow swarms.
performance-optimizer
Analyze and optimize code performance, identify bottlenecks, and suggest improvements.
performance-profiling
Find real performance problems with measurement, not guesses. Invoke when something is slow, or you're tempted to "optimize" without data.
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.