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 pandysp/claude-plugins --skill transcribegit clone --depth 1 https://github.com/pandysp/claude-pluginsWrote 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/pandysp/claude-plugins/transcribe)<a href="https://agentmods.dev/skills/pandysp/claude-plugins/transcribe"><img src="https://agentmods.dev/badge/skills/pandysp/claude-plugins/transcribe/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/pandysp/claude-plugins/transcribe"><img src="https://agentmods.dev/badge/skills/pandysp/claude-plugins/transcribe.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 | $0.00090 | $0.01586 |
| Opus 5.5 | $0.00036 | $0.00634 |
| Sonnet 5.5 | $0.00018 | $0.00317 |
| Haiku 4.5 | $0.00009 | $0.00159 |
Grade A, and why
transcribe 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 25d 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.
Transcription
Machine transcripts look finished even when they are wrong, and each run costs money. So the work has four steps: collect the audio, transcribe it with the script, put the notes where the user keeps them, and mark what the transcript probably got wrong. The script does step 2. Steps 3 and 4 need judgment, so there is no script for them.
1. Collect the audio
Pick a working folder with room, separate from where the notes will end up.
Below it is called <base>. Put the audio in <base>/audio/. Audio files go in
as they are. For a video, extract its sound first; that is much quicker than
uploading the whole video:
mkdir -p "<base>/audio"
ffmpeg -n -i "<recording>.mp4" -vn -acodec copy "<base>/audio/<recording>.m4a"
- Keep the recording's filename, without its extension. It ties the note back to the recording.
-nstops ffmpeg from overwriting a file that already exists. If it stops, pick another name.- If ffmpeg says "could not find tag for codec", the sound is in a format the
.m4afile can't hold as it is. Convert it instead: replace-acodec copywith-c:a aac -b:a 128k.
2. Transcribe
python3 "<skill-dir>/scripts/transcribe.py" --base-dir "<base>"
<skill-dir>is the folder this file was loaded from. Write the script's path out in full and run it from the user's folder, because--base-diris read relative to where you are.- The script writes one note per recording to
<base>/transcripts/<name>.md(--out-dirchanges that). If that name is taken, it writes<name>.<transcript id>.mdinstead; it never overwrites a note. The header block at the top of the note (frontmatter) lists the language, the speakers, the length and the model. - Keep
<base>after the run. Its.transcribe/folder records what has been paid for, so running the script again is safe: finished recordings are skipped and an interrupted job continues instead of being paid for twice. - One case needs the user: if the connection broke right after a recording was
submitted, the script can't know whether AssemblyAI got it, so it stops for
that recording. Ask the user to check the transcripts in their AssemblyAI
dashboard. Only if it isn't there, run again with
--retranscribe. - Recordings are sent to AssemblyAI's servers in the EU and deleted there once
the result is saved in
.transcribe/. A deletion that fails is retried on every later run. Change that (--region us,--keep-remote) only if the user asks. A folder from an earlier version of this skill (with a.transcribedfile) is skipped; those transcripts may still be stored on AssemblyAI's US servers. - If the script exits with 1, some recordings failed or a deletion is still pending. Its output names them and says why; running it again picks up where it stopped. If it exits with 2, the run stopped (no API key, another run still busy, no audio found, a damaged state file); recordings finished before that are listed and kept. Pass the message on to the user.
- The settings the script sends to AssemblyAI are chosen on purpose. Read the
comment above
REQUESTin the script before changing any of them.
What ships with it
1 file 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.
- 25d ago First seen · 129 lines · 90 tokens per session scan A cb048b6ba666
transcribe is a skill published in the GitHub repository pandysp/claude-plugins (6 stars, last pushed 7d ago), licensed MIT. It adds 90 tokens to every session and 1,586 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 2026-10-03.
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…