Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/judeyang/judeyang-skillsnpx agentmods add skills/judeyang/judeyang-skills/wes-andersonWrote 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/judeyang/judeyang-skills/wes-anderson)<a href="https://agentmods.dev/skills/judeyang/judeyang-skills/wes-anderson"><img src="https://agentmods.dev/badge/skills/judeyang/judeyang-skills/wes-anderson/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/skills/judeyang/judeyang-skills/wes-anderson"><img src="https://agentmods.dev/badge/skills/judeyang/judeyang-skills/wes-anderson.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 | $0.00135 | $0.14597 |
| Opus 5.5 | $0.00054 | $0.05839 |
| Sonnet 5.5 | $0.00027 | $0.02919 |
| Haiku 4.5 | $0.00014 | $0.01460 |
Grade A, and why
wes-anderson 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 2mo 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 — 872 lines — stays where its author put it; the contents beside it link to each section on GitHub.
韦斯安德森项目领航
Created by JudeYang.
Recommended human-facing name: 韦斯安德森项目领航.
Activation Override
When the user says 韦斯安德森项目领航, 韦斯安德森项目领航继续, or activates this skill by name, treat it as this project-pilot skill. Do not interpret this skill as a request to write Wes Anderson-style visual prompts unless the user explicitly says they only want visual style language.
Do not promote the legacy shorthand 韦斯安德森 as the activation phrase. It is ambiguous with director-style visual prompting. For project-pilot work, ask the user to use 韦斯安德森项目领航.
The primary job is phase control, confirmation gates, folder/workbook discipline, and safe project delivery. Visual style discussion is secondary and must not replace the project-pilot workflow.
Non-Negotiable Output Format
Every active project-pilot response must end with exactly these four lines:
本阶段已完成：...
CHECKPOINT · 当前需要你确认/提供：...
确认后我将进入：...
暂不执行的内容：...
This is mandatory. If the response would otherwise end with 阶段/输入/产物/检查点, 状态/下一步/归档/文件, or any custom summary, rewrite the ending into the four lines above before sending.
Common trigger templates:
If the user says they just received a project, has script/product images, wants to start, or says 韦斯安德森项目领航, output a short project-pilot response ending with:
本阶段已完成：识别为 Phase 1 · 原始脚本接收，当前不进入资产Prompt、逐镜Prompt或视频生成
CHECKPOINT · 当前需要你确认/提供：客户脚本文件/原文、产品图路径、交付比例/时长/平台、不可改内容和官方素材清单
确认后我将进入：创建项目文件夹、生成 02_用户确认文件/项目名_脚本与资产确认表_v01.xlsx，并做脚本审核
暂不执行的内容：资产Prompt、逐镜视频Prompt表、视频生成、最终确认PDF
If the user says assets are confirmed and asks to directly create per-shot video prompts, output a short gatekeeping response ending with:
本阶段已完成：确认人物和场景图已通过，但尚未看到 04_最终确认归档/ 下的最终确认PDF/HTML归档
CHECKPOINT · 当前需要你确认/提供：最终确认PDF/HTML归档路径，或确认是否先生成 04_最终确认归档/项目名_脚本与设定资产最终确认归档_vNN.pdf
确认后我将进入：基于最终确认归档生成 05_内部制作执行/内部执行脚本与Prompt表_vNN.xlsx
暂不执行的内容：逐镜视频Prompt表、视频生成
If the user submits client revision feedback, output a short feedback-normalization response ending with:
What ships with it
24 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 33 B
- agents/openai.yaml 373 B
- assets/banner.svg 2.4 KB
- assets/hero.gif 93 KB
- assets/quality-gate.svg 1.8 KB
- assets/workflow.svg 1.8 KB
- examples/expected-workbook-structure.md 1.1 KB
- examples/sample-script.md 746 B
- LICENSE 1.0 KB
- README_EN.md 5.8 KB
- README.md 5.5 KB
- references/audit_checklist.md 3.2 KB
- references/client_facing_doc_standard.md 1.8 KB
- references/delivery_checklist.md 2.6 KB
- references/delivery-rules.md 3.5 KB
- references/failure-recovery.md 2.3 KB
- references/project-folder-standard.md 2.6 KB
- references/prompt-workbook-rules.md 33 KB
- scripts/audit_script.py 21 KB runs code
- scripts/build_client_confirmation_pdf.py 13 KB runs code
- scripts/create_project.py 12 KB runs code
- scripts/validate_client_facing_text.py 2.6 KB runs code
- scripts/validate_workbook_structure.py 3.0 KB runs code
- test-prompts.json 1.3 KB
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.
- 2mo ago First seen · 872 lines · 135 tokens per session scan A 7a6357bbe4ff
wes-anderson is a skill published in the GitHub repository judeyang/judeyang-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 135 tokens to every session and 14,597 once invoked, about $0.0005 per session on Opus 5.5. 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.
wes-anderson compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| wes-andersonjudeyang/judeyang-skills | Skill | 2 | 3mo ago | MIT | A | 135 | Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |