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 tomzx/agents --skill record-asciinemagit clone --depth 1 https://github.com/tomzx/agentsWrote 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/tomzx/agents/record-asciinema)<a href="https://agentmods.dev/skills/tomzx/agents/record-asciinema"><img src="https://agentmods.dev/badge/skills/tomzx/agents/record-asciinema/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/tomzx/agents/record-asciinema"><img src="https://agentmods.dev/badge/skills/tomzx/agents/record-asciinema.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 | $0.00046 | $0.01614 |
| Opus 5.5 | $0.00018 | $0.00646 |
| Sonnet 5.5 | $0.00009 | $0.00323 |
| Haiku 4.5 | $0.00005 | $0.00161 |
Grade A, and why
record-asciinema 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 7d 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Record CLI Demo (asciinema)
Record a terminal demonstration with asciinema, render the .cast to a GIF (or SVG fallback) so it can be embedded inline in a GitHub PR or comment, and return the path to the rendered asset.
This is the recording primitive for CLI changes.
For web UI changes, use /record-playwright.
Recording principle: show commands
Always display the commands being run in the recording so viewers can see what was executed and reproduce it. Hide commands only when it is appropriate for the purpose of the demo (e.g. focusing purely on output, or a polished marketing-style demo where the command is irrelevant). When in doubt, show the command.
Prerequisites
asciinemainstalled- One of
agg,asciicast2gif, orsvg-term-cli(which provides thesvg-termbinary) installed (for rendering).aggis preferred (fastest, best quality). - If none are installed, the skill still returns the raw
.castwith playback instructions.
Inputs
The skill is driven by the following inputs. Set them from context, or accept them from the command line.
| Input | Meaning | Default |
|---|---|---|
$RECORD_SLUG ($1) |
Filename slug for the recording, e.g. verbose-flag |
demo |
$RECORD_TITLE |
Human-readable title shown in the asciinema player | CLI demo |
$RECORD_DIR |
Output directory for .cast / .gif |
/tmp/record-asciinema |
$RECORD_COMMAND ($2..) |
A single command to record non-interactively (single-shot demos) | (none; interactive mode) |
If $RECORD_COMMAND is provided, the demo runs that one command and exits.
If not, the skill drops into an interactive asciinema shell where the agent types the relevant commands and exits.
Workflow
Inputs resolved (slug, title, dir, command?)
|
v
asciinema available?
/ \
Yes No
| |
v v
Record .cast Return nothing,
caller falls back to text
|
v
Render to GIF (agg -> asciicast2gif -> svg-term)
|
v
Return rendered asset path (+ raw .cast)
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.
- 7d ago Changed 530587f0b604
- 17d ago Changed · +5 lines f1436e318124
- 22d ago Changed · +12 lines 93340782d8c2
- 1mo ago First seen · 162 lines · 46 tokens per session scan A 9bffa476df34
record-asciinema is a skill published in the GitHub repository tomzx/agents (13 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 1,614 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 2026-09-03.
Other skills, from other repositories
pdf-backends
Xberg PDF extraction: native/Pdfium backend selection, rendering, encryption, OCR fallback, capability gaps. Use for PDF engine work.
python-execution-fallback
Four-step recovery workflow for code execution failures when inline Python fails.
pandoc-pdf-error-resolution
Systematic debugging workflow for pandoc PDF conversion errors.
pptx-debug-workflow
Systematic debugging workflow for python-pptx presentation generation.
openpyxl-sandbox-workaround
Use runshell with inline Python as a fallback when executecodesandbox fails for openpyxl/spreadsheet operations.
pandoc-unicode-sanitize
Pre-process Markdown to replace non-ASCII characters before pandoc PDF conversion.