Borrowing it
Nothing to install: this file belongs to EmiyaKatuz/crispasr-agent-transcriber. 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/EmiyaKatuz/crispasr-agent-transcriber/master/AGENTS.mdgit 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/instructions/emiyakatuz/crispasr-agent-transcriber/agents-md)<a href="https://agentmods.dev/instructions/emiyakatuz/crispasr-agent-transcriber/agents-md"><img src="https://agentmods.dev/badge/instructions/emiyakatuz/crispasr-agent-transcriber/agents-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/instructions/emiyakatuz/crispasr-agent-transcriber/agents-md"><img src="https://agentmods.dev/badge/instructions/emiyakatuz/crispasr-agent-transcriber/agents-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 | $0.00387 | $0.00387 |
| Opus 5.5 | $0.00155 | $0.00155 |
| Sonnet 5.5 | $0.00077 | $0.00077 |
| Haiku 4.5 | $0.00039 | $0.00039 |
Grade A, and why
crispasr-agent-transcriber AGENTS.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 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
Project Instructions
This repository builds local-only transcription helpers for Codex and MCP agents.
- Do not upload media to cloud transcription services.
- Prefer the CrispASR HTTP server and
/v1/audio/transcriptions. - Do not automate the CrisperWeaver GUI as the main path.
- Keep file access narrow: accept local files only, validate paths, and reject URLs.
- Use ffmpeg with argument lists and
shell=False. - Do not commit model files, audio/video files, transcripts, generated outputs, or temp WAVs.
- Do not trigger model downloads during verification. If a local model is missing, stop and tell the user what to download.
- Before reporting back, run the available tests and explain the outcome in plain language.
Plugin structure
This repository is also a Codex plugin. The plugin manifest is at
.codex-plugin/plugin.json, and the MCP server config is at .mcp.json.
- Skills live in
skills/crispasr-transcription/. - The MCP server lives in
mcp_server/crispasr_mcp/. - Plugin assets (icons, README) live in
assets/. - Installation instructions are in
docs/plugin_install.md.
When modifying the plugin manifest or MCP config, keep paths relative to the repository root so the plugin works when cloned to any location.
npm installer
The npm/ directory contains the public npx installer.
- Keep its version synchronized with
pyproject.toml,plugin.json, andserver.json. - Never add model downloads to the installer.
- Verify GitHub Release SHA-256 checksums before extracting plugin files.
- Preserve
models/,bin/, andoutputs/during updates and normal removal. - Run
npm testandnpm pack --dry-runfrom thenpm/directory after changes.
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 · 38 lines · 387 tokens per session scan A f20ba5805eea
crispasr-agent-transcriber AGENTS.md is an instructions file published in the GitHub repository EmiyaKatuz/crispasr-agent-transcriber (1 stars, last pushed 4mo ago), licensed MIT. It adds 387 tokens to every session, about $0.0015 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-agent-transcriber AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| crispasr-agent-transcriber AGENTS.mdEmiyaKatuz/crispasr-agent-transcriber | Instructions file | 1 | 4mo ago | MIT | A | 387 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |