Borrowing it
Nothing to install: this file belongs to samson-art/transcriptor-mcp. 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/samson-art/transcriptor-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/samson-art/transcriptor-mcpWrote 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/samson-art/transcriptor-mcp/agents-md)<a href="https://agentmods.dev/instructions/samson-art/transcriptor-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/samson-art/transcriptor-mcp/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/samson-art/transcriptor-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/samson-art/transcriptor-mcp/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 | $0.02948 | $0.02948 |
| Opus 5.5 | $0.01179 | $0.01179 |
| Sonnet 5.5 | $0.00590 | $0.00590 |
| Haiku 4.5 | $0.00295 | $0.00295 |
Grade A, and why
transcriptor-mcp AGENTS.md scanned grade A with 1 finding 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 20d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- Tests are next to their module. `youtube.test.ts` mocks `node:child_process` and never spawns yt-dlp. Each module with state exports reset helpers for tests. How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Shared context for every coding agent and contributor. This file holds only the facts that you cannot infer from the code. The process is in CONTRIBUTING.md and in .claude/skills/. The decisions are in docs/adr/.
transcriptor-mcp is an MCP server (8 tools, 4 widgets) and a REST API. Both wrap yt-dlp to fetch transcripts, metadata and frames from YouTube and 10 other platforms. It is TypeScript, ESM, Node 22 and Jest.
Commands
npm ciinstalls dependencies and the husky pre-commit hook. Run it in every clone and every git worktree. Without it, git runs no pre-commit hook in that checkout.make check-no-smokeis the gate: format-check, lint, typecheck, Jest, build. CI, pre-commit and the publish workflow all run it. It must be green before you say you are done.npx jest src/youtube.test.ts -t '<name>'runs one suite or one test.npm run buildrunstsctodist/, then four vite builds todist/ui/<app>.html. The server reads those HTML files at runtime.- To run locally:
npm run build, thennpm run start:mcp(stdio),start:mcp:http(port 4200) orstart(REST, port 3000). You needyt-dlponPATH,ffmpegfor frames, andffprobeforWHISPER_MAX_DURATION_SECONDS. Thedev,dev:mcpanddev:mcp:httpscripts currently fail:ts-node-devcannot load this ESM package. node .claude/hooks/guards.check.mjsself-checks the agent hooks. It needsghand network access.
Map
src/mcp-core.ts: the whole MCP surface (tools, prompts, resources, widget resources and CSP,withToolErrorHandling, the per-call log line).src/mcp.tsis the stdio entry.src/mcp-http.tsis stateless Streamable HTTP (ADR 001).src/index.tsis the REST API (5 of the 8 tools).src/validation.ts: the service layer shared by MCP and REST (URL and language checks, cache, auto-discovery in the original language, Whisper fallback, in-flight dedupe).src/youtube.ts: theyt-dlp/ffmpegruns, failure classification, cookies copies. The startupyt-dlp --versioncheck is insrc/yt-dlp-check.ts.src/errors.ts(typed errors and caller texts),src/subtitle-rate-limit.ts(429 hold),src/canary.ts,src/metrics.ts,src/cache.ts(optional Redis),src/whisper*.ts.ui/: React widgets.web/: static site.legal/: public terms.load/: k6 scripts.
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.
- 20d ago Changed · +1 lines · +67 tokens per session f5c256df19ed
- 21d ago First seen · 104 lines · 2,881 tokens per session scan A 13de9ab31f56
transcriptor-mcp AGENTS.md is an instructions file published in the GitHub repository samson-art/transcriptor-mcp (23 stars, last pushed 10d ago), licensed MIT. It adds 2,948 tokens to every session, about $0.0118 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-26.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).