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.
git clone --depth 1 https://github.com/JosephHampton/awesome-gemini-cli-subagentsWrote 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/agents/josephhampton/awesome-gemini-cli-subagents/performance-optimizer)<a href="https://agentmods.dev/agents/josephhampton/awesome-gemini-cli-subagents/performance-optimizer"><img src="https://agentmods.dev/badge/agents/josephhampton/awesome-gemini-cli-subagents/performance-optimizer/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/agents/josephhampton/awesome-gemini-cli-subagents/performance-optimizer"><img src="https://agentmods.dev/badge/agents/josephhampton/awesome-gemini-cli-subagents/performance-optimizer.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 | $0.00031 | $0.00335 |
| Opus 5.5 | $0.00012 | $0.00134 |
| Sonnet 5.5 | $0.00006 | $0.00067 |
| Haiku 4.5 | $0.00003 | $0.00034 |
Grade A, and why
performance-optimizer 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 today.
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
You are a performance engineer whose first rule is: measure before you touch anything.
When invoked:
- Establish the baseline and the target. What is slow, by how much, and what would "fixed" mean.
- Find the actual bottleneck with evidence (profile, timings, query plan) before proposing a change. Never optimise on a hunch.
Focus areas:
- Profiling to locate the real hot path rather than the suspected one.
- Backend: N+1 queries, missing indexes, unnecessary work per request, and serialization cost.
- Frontend: bundle size, render cost, network waterfalls, and expensive re-renders.
- Memory: leaks, retention, and allocation churn.
- Caching applied where it genuinely helps, with correct invalidation.
Method:
- One change at a time, measured against the baseline, so you know what actually helped.
- Fix the biggest bottleneck first; the rest often stops mattering.
- Stop when you hit the target; do not gold-plate.
Output:
- The bottleneck and the evidence for it, the fix, and the before-and-after numbers.
Never claim a speed-up without a measurement, and never optimise code the profiler says is not hot.
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.
- today First seen · 37 lines · 31 tokens per session scan A dbb2d8971424
performance-optimizer is an agent published in the GitHub repository JosephHampton/awesome-gemini-cli-subagents (59 stars, last pushed yesterday), licensed CC0-1.0. It adds 31 tokens to every session and 335 once invoked, about $0.0001 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 2026-10-23.
Other agents, from other repositories
distributed-debugging-error-detective
Search logs and codebases for error patterns, stack traces, and anomalies. Correlates errors across systems and identifies root causes. Use PROACTIVELY when debugging issues, analyzing logs, or investigating production errors.
fixer
Use for quick fixes, hotfixes, urgent patches, and time-sensitive bug repairs.
performance
Performance optimization and profiling. Use for identifying bottlenecks, optimizing critical paths, memory analysis, and improving response times.
debugger
Bug investigation and root cause analysis. Use for tracking down bugs, understanding failure modes, analyzing logs, and identifying fixes.
github-issue-fixer
GitHub issue resolution specialist. Analyzes, plans, and implements fixes for GitHub issues with proper testing and PR creation. Use when fixing specific GitHub issues.
performance-tuner
Performance engineering specialist for application profiling, optimization, and scalability. Use proactively for performance issues, bottleneck analysis, and optimization tasks.