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 agentmods add agents/otterlyspacelabs/speekify/dependencies-integrationsgit clone --depth 1 https://github.com/OtterlySpaceLabs/speekifyWrote 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/agents/otterlyspacelabs/speekify/dependencies-integrations)<a href="https://agentmods.dev/agents/otterlyspacelabs/speekify/dependencies-integrations"><img src="https://agentmods.dev/badge/agents/otterlyspacelabs/speekify/dependencies-integrations.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00418 |
| Opus 5 | $0.00000 | $0.00209 |
| Sonnet 5 | $0.00000 | $0.00084 |
| Haiku 4.5 | $0.00000 | $0.00042 |
Grade A, and why
dependencies-integrations 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 4d 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
Dependencies And Integrations
- External runtime dependencies include
supertonic,httpx,trafilatura,yt-dlp,pypdf(local PDF text extraction inextract_common.read_document),langdetect,torch,transformers,rich,typer(pinned<0.26because newer typer vendors click and breaks the click-based CLI error handling), andclick(imported directly byspeekify.__main__). - MCP support is provided by the
mcpdependency andspeekify.mcp_server:main, reached through the singlespeekify mcpsubcommand dispatched inspeekify.__main__.main(there is no separatespeekify-mcpentry point, so the same command works for pip/uv installs and the Homebrew/PyInstaller single-binary build); client-specific setup notes live indocs/mcp-clients.md. translation.pychoosesmpswhen available, otherwise CPU, and disables transformers progress output.extract.pyusesyt-dlpmetadata to locate English YouTube subtitles/transcripts. Other URLs use trafilatura-based generic extraction, with Medium feed/GraphQL fallbacks for blocked Medium articles.- Local-file sources are read in
extract_common.py:is_document_path_inputdetects an existing.txt/.md/.text/.pdfpath (skipped when--urlforces URL mode), andread_documentreads text files via stdlib and PDFs viapypdf.workflow.resolve_contenttries URL extraction, then file reading, then plain text. logging_utils.configure_logger()quiets noisy Hugging Face/transformers loggers and prunes records older than 14 days.- Standalone macOS packaging uses PyInstaller through
scripts/build_standalone_macos.sh; Homebrew formula rendering is handled byscripts/render_homebrew_formula.py.
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.
- 4d ago First seen · 10 lines · 0 tokens per session scan A 06ccad3ed10d
dependencies-integrations is an agent published in the GitHub repository OtterlySpaceLabs/speekify (10 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 418 tokens. 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 agents, from other repositories
multimodal-specialist
Vision, audio, image and video generation, and multimodal processing specialist. Integrates Claude Opus 4.8, GPT-5, Gemini 2.5/3, GPT Image 2, Nano Banana Pro, Kling 3.0, Sora 2 and Veo 3.1 for analysis, generation, transcription and multimodal RAG.
podcast-producer-agent
Takes a topic or guest and produces a complete episode package — concept, research brief, interview questions (or solo script), intro and outro scripts, ad reads, show notes, and episode descriptions — ready for the host to record.
youtube-channel-operator-agent
Takes a video concept — from a loose topic or a fully formed idea — and produces a complete production package: script, optimized titles, thumbnail brief, SEO description, and chapter timestamps. Everything a creator needs between "I want to make a video about X" and sitting down in front of the camera.
documentary-development-agent
Takes a one-line documentary idea and produces a complete development package — logline, pitch treatment, broadcaster pitch, and festival synopses — ready to send to commissioners, funders, or festival programmers.
script-agent
Owns the words the creator speaks — generates hook options across multiple frameworks, then writes three complete, camera-ready script variants engineered for retention, each with a cold open, beat-level evidence, pattern interrupts, b-roll cues and a single closing CTA. Also produces the clean recording script the…
ideation-agent
Turns a research dossier and the channel profile into exactly six ranked, pitchable idea cards — each with a one-sentence thesis, a literal spoken hook line, a named promise, a differentiation claim and an honest risk. Use when the creator asks what to make next, when a research pass has finished and needs converting…