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.
npx skills add Desquared/agents-rules-skills --skill shared-perf-comparison-videogit clone --depth 1 https://github.com/Desquared/agents-rules-skillsWrote 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/skills/desquared/agents-rules-skills/shared-perf-comparison-video)<a href="https://agentmods.dev/skills/desquared/agents-rules-skills/shared-perf-comparison-video"><img src="https://agentmods.dev/badge/skills/desquared/agents-rules-skills/shared-perf-comparison-video/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/skills/desquared/agents-rules-skills/shared-perf-comparison-video"><img src="https://agentmods.dev/badge/skills/desquared/agents-rules-skills/shared-perf-comparison-video.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 | $0.00144 | $0.01850 |
| Opus 5.5 | $0.00058 | $0.00740 |
| Sonnet 5.5 | $0.00029 | $0.00370 |
| Haiku 4.5 | $0.00014 | $0.00185 |
Grade A, and why
shared-perf-comparison-video 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 6d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Before/after performance video
Produce a clip in the style people recognise from platform migration announcements: two phones on a white ground, Before on the left and After on the right, both apps launching on the same frame, a running clock under each that freezes green the instant that app is usable, and a card at the end with the numbers.
The rendering is the easy part and the bundled scripts do it. The work worth your attention is deciding when each app is "ready", because that single judgement is the entire claim the video makes. Get it wrong and you have produced a confident, beautiful, wrong artefact that someone will show to their CTO.
What you need before starting
- Two screen recordings of the same journey, one per version/app. They do not need to be the same length, start at the same moment, or even be the same device — all of that is handled. They do need to be the same journey on comparable hardware.
- ffmpeg on PATH.
brew install ffmpegif missing. - If the person has not recorded yet, read
references/capture.mdfirst and tell them how to capture fairly. A biased recording cannot be rescued in the edit.
Set up the tooling once per working directory:
eval "$(/path/to/skill/scripts/bootstrap.sh)" # creates a venv, exports PERF_PY
Pipeline
1. Find the instants
Never scrub a timeline by eye and never trust the two files to start at the same moment — they never do. Let the pixels tell you:
"$PERF_PY" scripts/probe_moments.py "before.mov"
"$PERF_PY" scripts/probe_moments.py "after.mov"
This prints the clip's bursts of change: a launcher sitting still, then a spike when
the window transition fires, then quiet, then content landing, then quiet again. The
first burst's start is almost always the launch instant. A burst's settle is when the
picture stopped moving, which is your candidate for "ready".
Narrow in on anything ambiguous with --from/--to for per-frame detail, and export the
frames so you can actually look at them:
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 153 lines · 144 tokens per session scan A 8b5c76c373f3
shared-perf-comparison-video is a skill published in the GitHub repository Desquared/agents-rules-skills (4 stars, last pushed yesterday), licensed MIT. It adds 144 tokens to every session and 1,850 once invoked, about $0.0006 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 2026-09-24.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…