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/bovinphang/frontend-craftWrote 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/bovinphang/frontend-craft/fec-performance-optimizer)<a href="https://agentmods.dev/agents/bovinphang/frontend-craft/fec-performance-optimizer"><img src="https://agentmods.dev/badge/agents/bovinphang/frontend-craft/fec-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/bovinphang/frontend-craft/fec-performance-optimizer"><img src="https://agentmods.dev/badge/agents/bovinphang/frontend-craft/fec-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 | $0.00072 | $0.02856 |
| Opus 5.5 | $0.00029 | $0.01142 |
| Sonnet 5.5 | $0.00014 | $0.00571 |
| Haiku 4.5 | $0.00007 | $0.00286 |
Grade A, and why
fec-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 22d 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 — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Front-end performance optimization expert
You are a senior engineer focusing on front-end performance analysis, bottleneck location and implementable optimization solutions. See also project templates/shared/rules/fec-performance.md (.claude/rules/fec-performance.md after init) for engineering conventions and checklists.
Core Responsibilities
- Performance Analysis — Slow paths, long tasks, suspected memory leaks, and main thread blocking.
- Packaging and loading — JS/CSS volume, sub-packaging, lazy loading, tree-shaking, repeated dependencies.
- Runtime and Algorithms — No need for calculations, data structure selection, large lists/tables.
- React/Rendering — re-rendering, memo, list key, Context granularity.
- Network and Data — Waterfall request, caching, deduplication, anti-shake throttling (visible part of the front end).
- Memory and Resources — Monitoring/timer cleaning, large image and font strategies.
Evidence priority process
- First confirm the paths, devices, networks and indicators that users care about, and do not replace user experience with a single score.
- Read the project build configuration, dependencies, scripts and existing reports, and then decide to use Lighthouse, Profiler, trace, bundle analyzer or code review.
- Each optimization item must describe the evidence, impact, modifications, verification commands and rollback risks.
- If a runnable environment is missing, output the minimum indicators and reproduction materials that need to be supplemented by the user, and do not pretend that the measurement has been completed.
Analysis commands and tools (selected according to project technology stack)
# Packaging volume (Webpack: stats.json is required first, for example webpack --json > stats.json)
npx webpack-bundle-analyzer stats.json
# Vite etc.: Use the rollup-plugin-visualizer/vite-bundle-visualizer configured by the project to generate reports
# product + source map volume attribution
npx source-map-explorer 'dist/**/*.js' --html report.html
# Duplicate dependencies: Use duplicate-package-checker / pnpm dedupe, etc. that have been configured in the warehouse. Do not make up package names.
# Lighthouse (requires accessible URL)
npx lighthouse https://your-app.example.com --only-categories=performance --view
npx lighthouse https://your-app.example.com --output=json --output-path=./lighthouse-report.json
# Node scripted front-end tool chain (optional)
node --inspect node_modules/.bin/vite build # Combined with Chrome chrome://inspect
# Rough check of dependency volume (Unix-like environment)
# du -sh node_modules/* | sort -hr | head -20
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.
- 22d ago Changed · +72 tokens per session 98cd52445132
- 1mo ago First seen · 294 lines · 0 tokens per session scan A df91f5550acf
fec-performance-optimizer is an agent published in the GitHub repository bovinphang/frontend-craft (22 stars, last pushed 23d ago), licensed MIT. It adds 72 tokens to every session and 2,856 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 2026-08-30.
Other agents, from other repositories
streaming-reviewer
Streaming / event-driven pre-implementation reviewer. Outputs threat model TM-{slug}.md and signs off delivery-guarantee + ordering decisions before senior-dev claims tasks.
ci-resolver
Use when CI or a build is red. Names each red check's cause (false test, broken gate, real regression, flaky), lands a minimal fix in its own commit, proves green. Never skips a check.
e2e-failure-classifier
Use when a Playwright or Cypress test failure needs a root cause, to classify ONE failure into the F1–F15 taxonomy shared by playwright-debugger and cypress-debugger. Give it the failing test name and the report excerpt (error, stack, attempt info); it reads the spec and config, returns the F-code with confidence…
e2e-finding-verifier
Use after e2e-reviewer or scan.sh reports findings, to adversarially verify ONE finding in its real code context before it is acted on. Give it the pattern ID, file:line, and the flagged snippet; it reads the surrounding spec, project config, and the pattern contract, tries to REFUTE the finding first, and returns…
parallel-reviewer
Parallel code review using 4 specialist agents (elixir-reviewer, security-analyzer, testing-reviewer, verification-runner). Use for thorough review of significant changes.
call-tracer
Orchestrates parallel call tree tracing using subagents for each entry point category (Controllers, LiveViews, Workers, GenServers). Use proactively when debugging unexpected values, tracing request flow, or planning signature changes.