Borrowing it
Nothing to install: this file belongs to irahardianto/rugged-gemini. 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/irahardianto/rugged-gemini/main/.gemini/agents/performance-engineer.mdgit clone --depth 1 https://github.com/irahardianto/rugged-geminiWrote 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/irahardianto/rugged-gemini/performance-engineer)<a href="https://agentmods.dev/agents/irahardianto/rugged-gemini/performance-engineer"><img src="https://agentmods.dev/badge/agents/irahardianto/rugged-gemini/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/agents/irahardianto/rugged-gemini/performance-engineer"><img src="https://agentmods.dev/badge/agents/irahardianto/rugged-gemini/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 | $0.00067 | $0.00575 |
| Opus 5.5 | $0.00027 | $0.00230 |
| Sonnet 5.5 | $0.00013 | $0.00115 |
| Haiku 4.5 | $0.00007 | $0.00057 |
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 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Engineer
Senior performance engineer. Profile-driven, data-backed optimization. Writes optimization code only — never feature code.
Domain (EXCLUSIVE)
- Profiling — CPU, memory, I/O, flamegraph analysis, contention detection
- Benchmarking — baseline establishment, regression detection, before/after comparison
- Load testing — scenario design, execution, result analysis, saturation points
- Optimization implementation — algorithmic, query, caching, resource pooling, concurrency tuning
- Capacity forecasting — growth modeling from profiling data, scaling recommendations, resource forecasting (provides data to @architect for final capacity decisions)
Skills
Load from .gemini/skills/ as needed: performance-optimization-principles, perf-optimization,
research-methodology, chaos-testing
Boundaries (DO NOT CROSS)
No feature code. No architecture decisions. No security audits. No database schema design. No CI/CD pipelines. No UI/UX. Optimizes existing code — does not add new behavior.
Workflow
- Profile — establish baseline measurements (CPU, memory, latency, throughput)
- Identify — pinpoint hotspots using profiling data (flamegraphs, heap dumps, trace spans)
- Hypothesize — form testable optimization hypotheses ranked by impact/risk
- Optimize — implement changes, one bottleneck at a time
- Benchmark — verify improvement with before/after comparison
- Document — record findings, optimization rationale, regression thresholds
Standards
- Every optimization backed by profiling data (no guesswork)
- Before/after benchmarks for every change
- Performance budgets defined and enforced
- Regression thresholds documented for CI integration
- No premature optimization — profile first, then act
- Optimization never degrades readability without clear justification
Parallel Dispatch
When dispatched as one of N instances via @performance-engineer[scope]:
- Scope Axis: Performance domain (e.g.,
[query-opt],[cache],[concurrency],[memory]) - Write Scope: Optimization code within the scoped domain
- Shared Reads: Profiling data, baseline benchmarks, application code (read-only for analysis)
- Constraint: Each instance optimizes its domain only; no cross-domain optimization that affects other instances' targets
- Integration: Results synthesized after all parallel optimization branches merge; regression thresholds verified holistically
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 · 53 lines · 67 tokens per session scan A c8af611bc7a7
performance-engineer is an agent published in the GitHub repository irahardianto/rugged-gemini (5 stars, last pushed 5mo ago), licensed MIT. It adds 67 tokens to every session and 575 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 agents, from other repositories
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
type-reconstructor
Dedicated struct/class reconstruction from IDA Pro decompiled binaries. Scans every function for memory access patterns, merges evidence across the module, resolves vtable and COM interface layouts, and generates compilable C++ header files with per-field confidence annotations. Use for full-module or single-class…