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/development-commandsgit 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/development-commands)<a href="https://agentmods.dev/agents/otterlyspacelabs/speekify/development-commands"><img src="https://agentmods.dev/badge/agents/otterlyspacelabs/speekify/development-commands.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 | $0.00235 |
| Opus 5 | $0.00000 | $0.00118 |
| Sonnet 5 | $0.00000 | $0.00047 |
| Haiku 4.5 | $0.00000 | $0.00023 |
Grade A, and why
development-commands 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
Development Commands
- Run focused tests while iterating, for example
uv run pytest tests/test_workflow.pyoruv run pytest tests/test_cli.py. - Exercise the CLI from source with
uv run speekify "Hello world",uv run speekify --lang fr "Hello world", orprintf 'Hello' | uv run speekify. - Quote URLs that contain shell-special characters such as
?or&, for exampleuv run speekify "https://www.youtube.com/watch?v=eSP7PLTXNy8", becausezshcan reject the command before Speekify starts. - Model warmup is
uv run speekify setup; by default it warms Supertonic and English-to-French translation. Use--skip-translationfor Supertonic-only setup. - Release validation and packaging are documented in
docs/release-procedure.md; the macOS binary and Homebrew formula are built by GitHub Actions (.github/workflows/release.yml) onrelease: published, reusing./scripts/build_standalone_macos.sh.
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 · 8 lines · 0 tokens per session scan A c9ae524b10c3
development-commands 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 235 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
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.
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…
repurpose-agent
Turns one finished or scripted video into a full cross-platform distribution plan — extractable Shorts with re-hooks, native per-platform adaptations, a day-by-day publication schedule, asset naming, and an effort/return ranking that tells a solo creator exactly what to skip. Also handles the reverse direction, a…
shorts-agent
Plans and writes YouTube Shorts — either a channel-level Shorts strategy (cadence, series, positioning, honest conversion expectations) or production-ready Shorts derived from a long-form video or written from scratch. Each Short ships a timed spoken script, a 1–3 second hook, on-screen text with safe zones, loop…
thumbnail-agent
Designs three deliberately different thumbnail concepts per video — Safe, Curiosity and Wildcard — each shipping a ready-to-paste image-generation prompt, overlay text, paired title, palette and a mobile legibility check. Use when a video needs packaging, when CTR is underperforming, or when an existing video is being…