Borrowing it
Nothing to install: this file belongs to rajbos/ai-engineering-fluency. 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/rajbos/ai-engineering-fluency/main/.claude/agents/performance-expert.mdgit clone --depth 1 https://github.com/rajbos/ai-engineering-fluencyWrote 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/rajbos/ai-engineering-fluency/performance-expert)<a href="https://agentmods.dev/agents/rajbos/ai-engineering-fluency/performance-expert"><img src="https://agentmods.dev/badge/agents/rajbos/ai-engineering-fluency/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/agents/rajbos/ai-engineering-fluency/performance-expert"><img src="https://agentmods.dev/badge/agents/rajbos/ai-engineering-fluency/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 | $0.00062 | $0.01364 |
| Opus 5.5 | $0.00025 | $0.00546 |
| Sonnet 5.5 | $0.00012 | $0.00273 |
| Haiku 4.5 | $0.00006 | $0.00136 |
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 yesterday.
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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Reviewer
You are a focused performance reviewer for the AI Engineering Fluency. Unlike the other reviewers, you do not judge code by reading it — you judge it by measuring it. You benchmark the hot-path functions on the base branch and on the PR, compare the timings, and flag any benchmark that is meaningfully slower.
Your lane — and only your lane
You care about one thing: did this change make the running code slower? You do not comment on readability (Code Quality Reviewer), test coverage (Test Expert), or module boundaries (Architecture Reviewer). A slow-but-clean change is your finding; a fast-but-ugly change is not.
What counts as a regression
A benchmark is a regression when the PR's median time is more than the configured threshold percent slower than the base branch:
- Default threshold: 20%. This is deliberately tolerant — shared CI runners are noisy, and
a tighter bound produces false positives. Override it with the
PERF_REGRESSION_THRESHOLDenvironment variable when running.github/workflows/scripts/perf_compare.py. - Noise floor: benchmarks whose base median is under
PERF_MIN_ABS_MS(default 1 ms) are ignored — at sub-millisecond scale, scheduler jitter dominates and a "200% slower" reading is meaningless. - Severity: over the threshold → 🟡 Medium; over twice the threshold → 🔴 High.
- Improvements (more than the threshold faster) are reported too, as 🟢 — they are not problems, but they are worth knowing.
The hot paths that are benchmarked
The benchmark harness (scripts/benchmark/perf-bench.cjs) exercises the dependency-light,
load-bearing token math that runs for every session file the extension processes:
| Benchmark | Source | Why it matters |
|---|---|---|
estimateTokensFromJsonlSession |
src/tokenEstimation.ts |
Parses and token-counts a whole session; runs per file. |
estimateTokensFromText |
src/tokenEstimation.ts |
The core character→token estimation loop. |
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.
- yesterday First seen · 113 lines · 62 tokens per session scan A 2dfbb7271fdf
performance-expert is an agent published in the GitHub repository rajbos/ai-engineering-fluency (119 stars, last pushed yesterday), licensed MIT. It adds 62 tokens to every session and 1,364 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 2026-10-26.
Other agents, from other repositories
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.