Borrowing it
Nothing to install: this file belongs to banshee-data/velocity.report. 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/banshee-data/velocity.report/main/.claude/skills/podcast-transcript/SKILL.mdgit clone --depth 1 https://github.com/banshee-data/velocity.reportWrote 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/banshee-data/velocity.report/podcast-transcript)<a href="https://agentmods.dev/skills/banshee-data/velocity.report/podcast-transcript"><img src="https://agentmods.dev/badge/skills/banshee-data/velocity.report/podcast-transcript/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/banshee-data/velocity.report/podcast-transcript"><img src="https://agentmods.dev/badge/skills/banshee-data/velocity.report/podcast-transcript.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 | $0.00068 | $0.01996 |
| Opus 5.5 | $0.00027 | $0.00798 |
| Sonnet 5.5 | $0.00014 | $0.00399 |
| Haiku 4.5 | $0.00007 | $0.00200 |
Grade A, and why
podcast-transcript 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: podcast-transcript
Produce a transcript the project can cite. The tool does the listening twice, with engines whose mistakes differ; this skill does what neither engine can: decide what was said where they disagree, notice where they agree on nonsense, punctuate, paragraph, and attribute each paragraph to a speaker. A check then holds the result to the evidence. The tool and its files are described in tools/podcast-transcribe/README.md.
The full text stays out of the repository. The repository is public, and docs/ and data/
are built into the docs site and the binary, so committing a transcript would republish someone
else's episode. The transcript is archived outside any checkout (the owner's archive is
/Volumes/lidar/lidar/transcripts), and documents carry only a summary in the project's own words,
short quotations, and a citation of the episode link with timestamps.
Usage
/podcast-transcript https://podcasts.apple.com/us/podcast/…/id1610029625?i=1000793374806
/podcast-transcript https://castro.fm/episode/esLjgi
/podcast-transcript https://open.spotify.com/episode/6CchCq5oCwRIGasE881NOf
Procedure
1. Preflight
df -h ~: the first run downloads about 4 GB of models; each episode needs its audio twice over (about 100 MB for half an hour). Stop and say so if the disk is short.make install-transcribe, which reuses engines already on PATH.python3 tools/podcast-transcribe/podcast-transcribe.py resolve <URL>and confirm the show, title and date are the episode the owner meant.
2. Transcribe
Run prepare <URL> in the background. Pass A (Whisper on CPU) takes about 0.7 times the episode's
length on an M1 Pro; pass B (Parakeet) takes seconds. It prints the work directory and the
agreement between passes. Agreement below about 95% means something went wrong (music beds, a
second language, a Whisper repetition loop): look at the worksheet before reconciling.
3. Establish the speakers
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 · 142 lines · 68 tokens per session scan A 09eeeb3ffb2d
podcast-transcript is a skill published in the GitHub repository banshee-data/velocity.report (11 stars, last pushed today), licensed Apache-2.0. It adds 68 tokens to every session and 1,996 once invoked, about $0.0003 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 2026-10-12.
podcast-transcript compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| podcast-transcriptbanshee-data/velocity.report | Skill | 11 | today | Apache-2.0 | A | 68 | Claude Code |
| analyzing-network-traffic-for-incidentsmukul975/Anthropic-Cybersecurity-Skills | Skill | 36k | 2mo ago | Apache-2.0 | A | 91 | Claude Code |
| analyzing-network-packets-with-scapymukul975/Anthropic-Cybersecurity-Skills | Skill | 36k | 2mo ago | Apache-2.0 | A | 75 | Claude Code |
| analyzing-network-traffic-with-wiresharkmukul975/Anthropic-Cybersecurity-Skills | Skill | 36k | 2mo ago | Apache-2.0 | B | 49 | Claude Code |
| whitebox-toolsznlgis/opengis-skills | Skill | 76 | 10d ago | MIT | A | 119 | Claude Code, Codex |
| performing-network-packet-capture-analysisxalgorix/xalgorix | Skill | 1.3k | yesterday | Apache-2.0 | C | 62 | Claude Code, Codex |
| pdalznlgis/opengis-skills | Skill | 76 | 10d ago | MIT | B | 90 | Claude Code, Codex |