Borrowing it
Nothing to install: this file belongs to pexoai/pexo-skills. 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/pexoai/pexo-skills/main/CLAUDE.mdgit clone --depth 1 https://github.com/pexoai/pexo-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/instructions/pexoai/pexo-skills/claude-md)<a href="https://agentmods.dev/instructions/pexoai/pexo-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/pexoai/pexo-skills/claude-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/pexoai/pexo-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/pexoai/pexo-skills/claude-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 | $0.00799 | $0.00799 |
| Opus 5 | $0.00400 | $0.00400 |
| Sonnet 5 | $0.00160 | $0.00160 |
| Haiku 4.5 | $0.00080 | $0.00080 |
Grade A, and why
pexo-skills CLAUDE.md 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 9d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — pexo-skills
Runtime contract for the Pexo skills. Claude Code reads this automatically; other agents should fetch it before using any skill.
What this is
Open-source agent skills for AI video production. Two categories:
Pexo agent (the product wrapper) — delegates to the hosted Pexo video agent:
pexo-agent → create project → chat (relay the user's words) → poll → deliver finished video
You are a delivery worker. Upload assets, relay the user's request verbatim, poll for status, and return the finished video. Pexo's backend does all creative work — scriptwriting, model selection, prompt engineering, music, subtitles. Do not add your own creative direction; it lowers quality.
Creative studios & prompters (core assets) — self-contained skills:
videoagent-video-studio → text/image-to-video across 7 models (hosted proxy, no keys)
videoagent-image-studio → image generation across 8 models
videoagent-audio-studio → TTS, music, SFX, voice cloning
videoagent-director → storyboard → generates images, clips, and audio shot by shot
seedance-2.0-prompter → expert Seedance 2.0 prompts
veo-3.2-prompter → expert Google Veo 3.2 prompts
Hard rules (pexo-agent)
- Reply to the user in their language.
- Relay the user's message to Pexo verbatim; only add asset tags for uploaded files.
- During
WAIT, only poll (pexo-project-get). Never callpexo-chatduringWAIT— it triggers duplicate production. - Deliver the full asset URL as plain text (all query params); never truncate or markdown-wrap it.
Config
~/.pexo/config:
PEXO_BASE_URL="https://pexo.ai"
PEXO_API_KEY="sk-<your-api-key>"
First-time setup or config errors → run skills/pexo-agent/scripts/pexo-doctor.sh.
Repository structure
pexo-skills/
├── README.md # public-facing description
├── INSTALL.md # human-facing install
├── INSTALL_FOR_AGENTS.md # agent-driven install runbook
├── CONTRIBUTING.md # PR workflow + quality bar + slug convention
├── CLAUDE.md # this file — runtime contract
├── LICENSE # MIT
├── VERSION # repo-wide version
├── scripts/
│ └── update-check.sh # opt-in version check (relayed by pexo-agent)
├── .claude-plugin/marketplace.json # Claude Code
├── .codex-plugin/plugin.json # OpenAI Codex
├── .cursor-plugin/plugin.json # Cursor
├── .github/workflows/ # validate, publish, awesome-list submit
└── skills/
├── pexo-agent/ # the product wrapper (shell → Pexo API)
├── videoagent-video-studio/
├── videoagent-image-studio/
├── videoagent-audio-studio/
├── videoagent-director/
├── seedance-2.0-prompter/
└── veo-3.2-prompter/
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.
- 9d ago First seen · 85 lines · 799 tokens per session scan A e53288687055
pexo-skills CLAUDE.md is an instructions file published in the GitHub repository pexoai/pexo-skills (777 stars, last pushed 19d ago), licensed MIT. It adds 799 tokens to every session, about $0.0040 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 2026-08-30.
Other instructions, from other repositories
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.