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 EmiyaKatuz/crispasr-agent-transcriber --skill crispasr-transcriptiongit clone --depth 1 https://github.com/EmiyaKatuz/crispasr-agent-transcriberWrote 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/emiyakatuz/crispasr-agent-transcriber/crispasr-transcription)<a href="https://agentmods.dev/skills/emiyakatuz/crispasr-agent-transcriber/crispasr-transcription"><img src="https://agentmods.dev/badge/skills/emiyakatuz/crispasr-agent-transcriber/crispasr-transcription/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/emiyakatuz/crispasr-agent-transcriber/crispasr-transcription"><img src="https://agentmods.dev/badge/skills/emiyakatuz/crispasr-agent-transcriber/crispasr-transcription.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 | $0.00063 | $0.00591 |
| Opus 5.5 | $0.00025 | $0.00236 |
| Sonnet 5.5 | $0.00013 | $0.00118 |
| Haiku 4.5 | $0.00006 | $0.00059 |
Grade A, and why
crispasr-transcription 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 2mo 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.
What it actually says
CrispASR Transcription
Use this skill when the user asks to transcribe local audio or video through CrispASR.
Rules:
- Never upload media to cloud services.
- Use
scripts/transcribe.py. - Use
--profile autounless the user specifies English or Chinese. - Do not let CrispASR auto-download models unless the user explicitly asks for that.
- Prefer
--models-dir modelsafter the recommended model bundle is installed. - If models are missing and the user wants downloads, use
--download-modelsor the MCPcrispasr_download_modelstool. - For managed auto mode without
--models-dir, pass both--english-modeland--chinese-model. - For an explicit profile, pass its local model path with
--model. - For auto language routing, pass
--lid-backend fireredand--lid-model. - Use MCP
understand_videowhen the user asks for video understanding, keyframes, screenshots, visual context, or agent-readable video analysis. - The firered LID backend is the default and recommended option; whisper is available as a fallback.
Example (auto mode with firered LID):
uv run python scripts/transcribe.py .\file.mp4 --profile auto --manage-server `
--models-dir models
Example (english profile with manual server):
uv run python scripts/transcribe.py .\file.wav --profile english `
--server-url http://127.0.0.1:8080
Model files
Download the recommended GGUF bundle with --download-models, or use these
filenames:
| Purpose | File | Source |
|---|---|---|
| English ASR | cohere-transcribe-q4_k.gguf |
Cohere Transcribe 03-2026 GGUF |
| Chinese ASR | qwen3-asr-1.7b-q4_k.gguf |
Qwen3-ASR GGUF |
| Language detection | firered-lid-q4_k.gguf |
FireRed LID GGUF |
Reference: references/crispasr_server.md.
What ships with it
2 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.
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.
- 2mo ago First seen · 50 lines · 63 tokens per session scan A 2853a949abcf
crispasr-transcription is a skill published in the GitHub repository EmiyaKatuz/crispasr-agent-transcriber (1 stars, last pushed 4mo ago), licensed MIT. It adds 63 tokens to every session and 591 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 2026-08-31.
crispasr-transcription compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| crispasr-transcriptionEmiyaKatuz/crispasr-agent-transcriber | Skill | 1 | 4mo ago | MIT | A | 63 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |