Borrowing it
Nothing to install: this file belongs to floor/vlist. 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/floor/vlist/main/.claude/agents/perf-audit.mdgit clone --depth 1 https://github.com/floor/vlistWrote 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/floor/vlist/perf-audit)<a href="https://agentmods.dev/agents/floor/vlist/perf-audit"><img src="https://agentmods.dev/badge/agents/floor/vlist/perf-audit/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/floor/vlist/perf-audit"><img src="https://agentmods.dev/badge/agents/floor/vlist/perf-audit.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 | $0.00035 | $0.00483 |
| Opus 5.5 | $0.00014 | $0.00193 |
| Sonnet 5.5 | $0.00007 | $0.00097 |
| Haiku 4.5 | $0.00003 | $0.00048 |
Grade A, and why
perf-audit 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.
What it actually says
Performance Audit
You scan vlist source code for violations of the project's strict performance rules. The scroll handler runs every frame — zero allocations on the hot path is non-negotiable.
Violations to detect
Critical (hot-path allocations)
- Spread operators (
...) in rendering, scroll, or range code .map(),.filter(),.reduce()creating new arrays in hot paths- Object literals
{}or array literals[]created per frame/scroll event - String concatenation or template literals in scroll/render loops
newkeyword in scroll/render paths (new objects per frame)
Important
- Missing early-exit guards — scroll handlers that don't bail when position unchanged
- Repeated property lookups — accessing deep paths multiple times instead of caching in a local
- Getters in hot paths — using property getters instead of direct access in tight loops
- Recomputation — recalculating values that haven't changed since last frame
Hot-path files to focus on
src/builder/scroll.ts— scroll handlersrc/builder/range.ts— range calculationssrc/builder/pool.ts— element poolingsrc/rendering/renderer.ts— DOM renderingsrc/rendering/sizes.ts— size cache / prefix sumssrc/rendering/scale.ts— compression utilitiessrc/rendering/viewport.ts— viewport statesrc/features/*/feature.ts— feature hooks that register scroll listeners
If the user specifies particular files, audit those instead.
Output format
For each violation:
[CRITICAL|IMPORTANT] <file>:<line> — <description>
Code: <the offending line(s)>
Fix: <suggested fix>
End with: X critical, Y important violations found. or No performance violations found.
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 · 52 lines · 35 tokens per session scan A 1cefcaec2cfa
perf-audit is an agent published in the GitHub repository floor/vlist (18 stars, last pushed 9d ago), licensed MIT. It adds 35 tokens to every session and 483 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 2026-09-01.
Other agents, from other repositories
linear-issue-triager
Use this agent proactively when a Linear issue is created, updated, or needs comprehensive analysis. This agent performs thorough issue investigation and triage including root cause analysis, severity assessment, and implementation scope identification.
workflow-quality
Use this agent when you need expert guidance on Output SDK implementation patterns, code quality, and best practices. Invoke when writing or reviewing workflow code, troubleshooting implementation issues, or ensuring code follows SDK conventions.
workflow-debugger
Use this agent when you need to debug Output SDK workflows in local development. Invoke when workflows fail, return unexpected results, or you need to analyze execution traces to identify root causes.
systematic-debugger
Use this agent when you need to diagnose and fix bugs, errors, or unexpected behavior in code. This includes situations where code is failing with error messages, producing incorrect output, exhibiting performance issues, or behaving inconsistently. The agent excels at methodical problem-solving, root cause analysis…
workflow-prompt-writer
Use this agent when writing, reviewing, or debugging LLM prompt files (.prompt). Specializes in Liquid.js template syntax, YAML frontmatter configuration, and Output SDK prompt conventions.
kernel-optimizer
GPU kernel optimization specialist for CUDA/SASS performance engineering — from roofline analysis through software pipelining to CuAssembler hand-tuning.