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 ansea09/agent-skills-and-protocols --skill speech-to-mdgit clone --depth 1 https://github.com/ansea09/agent-skills-and-protocolsWrote 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/ansea09/agent-skills-and-protocols/speech-to-md)<a href="https://agentmods.dev/skills/ansea09/agent-skills-and-protocols/speech-to-md"><img src="https://agentmods.dev/badge/skills/ansea09/agent-skills-and-protocols/speech-to-md/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/ansea09/agent-skills-and-protocols/speech-to-md"><img src="https://agentmods.dev/badge/skills/ansea09/agent-skills-and-protocols/speech-to-md.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 | $0.00102 | $0.01888 |
| Opus 5 | $0.00051 | $0.00944 |
| Sonnet 5 | $0.00020 | $0.00378 |
| Haiku 4.5 | $0.00010 | $0.00189 |
Grade A, and why
speech-to-md 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 11d 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Speech To Md
Document Roles
This SKILL.md is the executable routing contract. Keep detailed output and
runtime rules in references:
references/audio-bundle.md- canonical transcript bundle contract.references/runtime.md- local ASR engine, model, install, and support boundaries.references/extension-boundaries.md- refactoring thresholds for additional ASR engines, diarization, long-recording chunking, and cloud workflows.
Operating Contract
This skill handles trusted local speech recordings. It is separate from
doc-to-md: document conversion extracts existing file content, while speech
conversion performs ASR and must preserve uncertainty through timestamps,
engine metadata, and audit notes.
The public skill source does not bundle ASR models, Homebrew packages, Python
virtual environments, cloud credentials, or generated transcripts. Use a local
ASR engine deliberately. The first supported source-level engine contract is
whisper.cpp through a whisper-cli executable and a user-provided model file.
Cloud transcription, diarization, translation, speaker identification, long-recording chunking, and meeting-minutes generation are explicit advanced modes. Do not imply they work unless the needed engine, credentials, workflow, and output evidence contract have been installed and checked.
Route Selection
| Situation | Action |
|---|---|
Trusted local speech audio and whisper.cpp is configured |
speech-to-md audio-file -o audio-bundle --model /path/to/model.bin |
| Existing transcript should be packaged for LLM analysis | speech-to-md --transcript transcript.txt --source-audio audio-file -o audio-bundle |
User asks to convert audio through doc-to-md |
Route here; audio is outside doc-to-md core. |
| Speaker labels or diarization are required | Explain that the current local workflow does not provide diarization; use an explicit advanced engine later. |
| Untrusted, remote, hosted, or shared-user audio ingestion | Stop and require separate sandboxing and privacy review before processing. |
What ships with it
11 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.
- agents/openai.yaml 223 B
- README.md 4.9 KB
- references/audio-bundle.md 3.7 KB
- references/extension-boundaries.md 5.7 KB
- references/runtime.md 5.5 KB
- schemas/speech-to-md-doctor.schema.json 685 B
- schemas/speech-to-md-manifest.schema.json 945 B
- schemas/speech-to-md-segments.schema.json 783 B
- scripts/install.sh 590 B runs code
- scripts/regression_corpus.py 9.8 KB runs code
- scripts/speech-to-md 37 KB
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.
- 11d ago First seen · 188 lines · 102 tokens per session scan A b76435614433
speech-to-md is a skill published in the GitHub repository ansea09/agent-skills-and-protocols (2 stars, last pushed yesterday), licensed MIT. It adds 102 tokens to every session and 1,888 once invoked, about $0.0005 per session on Opus 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 2026-08-31.
Other skills, from other repositories
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
overleaf-sync
A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.