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 tallesborges/zdx --skill record-demosgit clone --depth 1 https://github.com/tallesborges/zdxWrote 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/tallesborges/zdx/record-demos)<a href="https://agentmods.dev/skills/tallesborges/zdx/record-demos"><img src="https://agentmods.dev/badge/skills/tallesborges/zdx/record-demos/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/tallesborges/zdx/record-demos"><img src="https://agentmods.dev/badge/skills/tallesborges/zdx/record-demos.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 35 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00109 | $0.01814 |
| Opus 5.5 | $0.00044 | $0.00726 |
| Sonnet 5.5 | $0.00022 | $0.00363 |
| Haiku 4.5 | $0.00011 | $0.00181 |
Grade A, and why
record-demos scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Record zdx demos (VHS)
Record zdx as GIFs / PNGs / MP4 using VHS. Tapes are declarative and deterministic (headless ttyd + ffmpeg, no visible window), so the same .tape regenerates the same clip every time.
Two things, both committed to this repo:
- Tapes + assets = project content. Feature recordings live in
docs/tapes/*.tapeand render intodocs/assets/*.gif|png, embedded inREADME.md. - This skill = the how. It holds the recipe and gotchas. It contains no GIFs.
Prerequisites (check once)
which vhs ffmpeg || brew install vhs # vhs pulls in ttyd; ffmpeg needed for gif/mp4
Build a zdx binary to record against:
cargo build -p zdx --bin zdx # debug; or: just build-release
BIN_DIR="$(cd target/debug && pwd)" # release/ for build-release
"$BIN_DIR/zdx" --version # sanity check
Critical gotchas (encode these in every tape)
unset NO_COLORin the hidden setup, before launching zdx. The agent runtime exportsNO_COLOR=1, which makes the whole TUI monochrome. This is the #1 mistake — always unset it.- Quote all paths in
Output/Screenshot.$ZDX_ARTIFACT_DIRcontains--, which breaks VHS's unquoted-path parser. - Put
$BIN_DIRon PATH in the hidden setup sozdxresolves as a bare command. - ttyd startup race: an occasional
could not open ttyd: ERR_CONNECTION_REFUSED— just re-run the same tape. - Quit the TUI with
Ctrl+Ctwice (or thequitcommand). - Real turns need a live model call (~40s with Opus [high]). Don't pad the end with a long fixed
Sleep— that leaves a "frozen" tail on the final frame. Instead end the turn withWait+Screen /marker/(see gotcha 8). Tools run inline (no approval gate in this setup). - Colors show during real turns, not on the launch screen. The empty launch screen is mostly white/gray; diffs (green/red), tool output, syntax highlighting, and the context-% indicator only light up once the agent responds.
- End real turns with
Wait+Screen /marker/, and the marker must be output-only.Wait+Screenmatches anything currently on screen — including your typed prompt, which stays visible in the conversation. So a marker copied from the prompt fires instantly (empty recording). Pick text that appears only after completion — e.g. a distinctive word the model will produce in its answer but that isn't in your prompt, or the turn-summary bar (Wait+Screen@60s /tool ·/). Add a smallSleep 1safter the Wait so the final frame reads.
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 · 129 lines · 109 tokens per session scan A 62fb23a59d03
record-demos is a skill published in the GitHub repository tallesborges/zdx (20 stars, last pushed yesterday), licensed MIT. It adds 109 tokens to every session and 1,814 once invoked, about $0.0004 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 skills, from other repositories
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…
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…
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…