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/pippit-dev/pippit-skills/pippit-skillnpx skills add Pippit-dev/pippit-skills --skill pippit-skillgit clone --depth 1 https://github.com/Pippit-dev/pippit-skillsWrote 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/skills/pippit-dev/pippit-skills/pippit-skill)<a href="https://agentmods.dev/skills/pippit-dev/pippit-skills/pippit-skill"><img src="https://agentmods.dev/badge/skills/pippit-dev/pippit-skills/pippit-skill.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 5.1 | $0.00099 | $0.01969 |
| Opus 5 | $0.00049 | $0.00984 |
| Sonnet 5 | $0.00020 | $0.00394 |
| Haiku 4.5 | $0.00010 | $0.00197 |
Grade A, and why
pippit-skill 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 6d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pippit Skill Workflow
Use this self-contained skill for overseas Pippit.ai workflows. It includes both backend script sets locally:
scripts/nest/: Pippit Nest AI generation, editing, reference uploads, progress polling, and result downloads.scripts/publish/: Social account lookup, video upload, scheduled publishing, task CRUD, and analytics.
No external Pippit skill directories are required. For local commands, resolve {baseDir} to this skill folder. For detailed publishing payload fields, read references/publishing-api.md.
Pippit Nest owns creative interpretation, prompt expansion, model choice, storyboarding, and workflow routing. The local agent should only upload references, pass the user's request through, poll progress, handle clarification requests, download results, and then publish the selected video when requested.
Route the Request
- Creative only: Use
scripts/nest/to generate/edit, poll, and download outputs. Stop after returning local files unless the user asks to publish. - Publish only: Use
scripts/publish/for existing local videos, bound account checks, scheduling, task CRUD, or analytics. - Create-to-publish: Use
scripts/nest/first, download the generated video, then usescripts/publish/to upload and schedule it. - Image-only output: Publishing supports video only. If the user wants to publish an image/poster, ask whether to generate or convert it into a video first.
Creative Request Handling
- Pass the user's creative or edit request to
scripts/nest/submit_run.py --messageas-is. Do not compress, summarize, rewrite, polish, translate, split, or add prompt language unless the user explicitly asks. - Keep one creative task as one Nest submission. Do not turn a single request into per-shot, per-scene, or per-asset runs unless the user explicitly asks for separate runs.
- Do not manually write storyboards, infer camera plans, analyze styles, choose models, or orchestrate sub-prompts locally. Let Pippit Nest do that work.
- When reference images or videos are provided, upload them and submit the original request with the returned asset IDs. Do not replace the user's wording with your own description of the references.
- When Pippit asks for clarification or interaction, show the question to the user and submit the user's answer to the same
thread_id; do not answer on the user's behalf.
What ships with it
18 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .gitignore 512 B
- references/command-map.md 2.6 KB
- references/publishing-api.md 9.3 KB
- scripts/nest/_common.py 17 KB runs code
- scripts/nest/download_results.py 4.9 KB runs code
- scripts/nest/get_thread.py 3.7 KB runs code
- scripts/nest/save_access_key.py 1.6 KB runs code
- scripts/nest/submit_run.py 2.2 KB runs code
- scripts/nest/upload_file.py 4.1 KB runs code
- scripts/publish/_common.py 10 KB runs code
- scripts/publish/batchcreate_schedule_task.py 6.3 KB runs code
- scripts/publish/delete_schedule_task.py 1.2 KB runs code
- scripts/publish/list_schedule_task.py 2.1 KB runs code
- scripts/publish/list_user_platform_account.py 479 B runs code
- scripts/publish/list_videos.py 1.9 KB runs code
- scripts/publish/save_access_key.py 1.7 KB runs code
- scripts/publish/update_schedule_task.py 4.4 KB runs code
- scripts/publish/upload_file.py 3.0 KB runs code
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.
- 6d ago First seen · 124 lines · 99 tokens per session scan A 244469cccaf5
pippit-skill is a skill published in the GitHub repository Pippit-dev/pippit-skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 99 tokens to every session and 1,969 once invoked, about $0.0005 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
剪辑环境的唯一管理者：就绪检查（skills 是否最新 → Runtime 是否配套）、Skills 更新激活、Runtime 安装与体检。用户说检查更新、安装剪辑环境、装播放器、检查剪辑环境、剪辑环境就绪了吗、配置转录凭证时使用；业务 Skill（剪口播/字幕/画面/导出）第 0 步也引用本 Skill 的就绪检查。不用于剪辑、字幕、画面、导出本身或项目数据迁移。.