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 skills/squared-lemons-ltd/podmule-plugin/draft-clipsnpx skills add Squared-Lemons-Ltd/podmule-plugin --skill draft-clipsgit clone --depth 1 https://github.com/Squared-Lemons-Ltd/podmule-pluginWhat 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 | $0.00049 | $0.00558 |
| Opus 5 | $0.00024 | $0.00279 |
| Sonnet 5 | $0.00010 | $0.00112 |
| Haiku 4.5 | $0.00005 | $0.00056 |
Grade A, and why
draft-clips 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Draft clips from an episode
A clip in PodMule is a short piece of content hung off an episode, headed for social distribution. This skill turns a recording into a set of draft clips grounded in what was actually said.
Find the moments before writing anything
The transcript is the source. search_transcripts scoped to the episode surfaces candidate moments; get_transcript_window expands each hit into the surrounding section with timestamps, which is what tells you whether a moment stands on its own or only makes sense after three minutes of setup.
What makes a good clip is a self-contained turn: a claim, a story with a beginning, a disagreement, a number that lands. What makes a bad one is a moment that needs the preceding question to parse. The timestamps are the honest test — if the interesting sentence starts thirty seconds into a window that only makes sense from the top, the clip is the whole window or it is nothing.
Aim for a handful of strong candidates rather than an exhaustive list. Five clips someone will actually cut beats twenty they have to triage.
Write from the transcript, not around it
Each clip carries a title and a description. Both should come from what was said. A title that paraphrases the actual line is findable later; a title that describes the episode generically is not.
Record where the moment is — the timestamp belongs in the description, because whoever cuts the video needs it and nothing else in the clip record carries it.
Create them as drafts
create_clip needs the episode id and a title, and takes description, tags and an external link. Clips land in draft state, which is the right place to leave them: the person whose show it is decides what ships.
Confirm the set with the user before creating, and show them the titles and timestamps rather than a count. Creating ten clips someone did not want is a mess to undo one at a time.
update_clip revises one afterwards. schedule_clip moves a clip to authorised with a publish time — that is a publishing decision, so it needs an explicit ask, not an inference from enthusiasm.
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.
- 2d ago First seen · 35 lines · 49 tokens per session scan A a52a5b1ae944
draft-clips is a skill published in the GitHub repository Squared-Lemons-Ltd/podmule-plugin (0 stars, last pushed 14d ago), licensed MIT. It adds 49 tokens to every session and 558 once invoked, about $0.0002 per session on Opus 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…