Borrowing it
Nothing to install: this file belongs to Wangnov/gpt-image-2-skill. 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/Wangnov/gpt-image-2-skill/main/CLAUDE.mdgit clone --depth 1 https://github.com/Wangnov/gpt-image-2-skillWrote 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/wangnov/gpt-image-2-skill/claude-md)<a href="https://agentmods.dev/instructions/wangnov/gpt-image-2-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/wangnov/gpt-image-2-skill/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/wangnov/gpt-image-2-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/wangnov/gpt-image-2-skill/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 | $0.00536 | $0.00536 |
| Opus 5.5 | $0.00214 | $0.00214 |
| Sonnet 5.5 | $0.00107 | $0.00107 |
| Haiku 4.5 | $0.00054 | $0.00054 |
Grade A, and why
gpt-image-2-skill 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 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.
What it actually says
gpt-image-2-skill
Rust workspace（crates/*）+ Tauri / Web 前端（apps/gpt-image-2-app）+ skill 包（skills/）。
发版（必须两步，缺一不可）
发版是两个独立流程，只跑第一步会让桌面 app 的内部更新失效：
-
just release patch（或minor/major）—— cargo-dist 流程：bump 版本、发布 crates.io、创建 GitHub Release、上传 CLI 安装包。tag push 后自动触发 "Release" workflow。 -
just release-tauri v<新版本>—— 手动触发 "Tauri App Release"（workflow_dispatch）：构建桌面 app 安装包，并生成、上传latest.json（tauri updater manifest）。不会随 tag 自动触发，必须手动跑。⚠️ 顺序铁律：第二步必须等第一步的 "Release" workflow 把 GitHub Release 建好之后再跑。两个流程都会创建同一个
v<版本>Release，但 cargo-dist 的gh release create不幂等、Tauri 的create-release幂等——若第二步抢跑，Tauri 会先把 Release 建出来，导致 cargo-dist 在 "Create GitHub Release" 撞already exists，整个 "Release" workflow 失败（CLI 安装包、npm/GHCR 触发一并丢失）。just release-tauri已内置scripts/release/wait-for-release.sh，会阻塞到 Release 的 assets 出现 cargo-dist 特有的dist-manifest.json（只验"Release 存在"防不住抢建后重试的场景）再 dispatch；若手动gh workflow run，务必自行跑该脚本或确认该 asset 已存在。
Tauri updater 的端点是 releases/latest/download/latest.json（见 apps/gpt-image-2-app/src-tauri/tauri.conf.json）。漏掉第 2 步，最新 Release 里就没有 latest.json，已安装的 app 检查更新会报：
Could not fetch a valid release JSON from the remote
发版完成判据：just release-tauri 触发的 workflow 跑成功，且对应 Release 的 assets 里能看到 latest.json。
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 · 19 lines · 536 tokens per session scan A 58de88f7cc4e
gpt-image-2-skill CLAUDE.md is an instructions file published in the GitHub repository Wangnov/gpt-image-2-skill (147 stars, last pushed 5d ago), licensed MIT. It adds 536 tokens to every session, about $0.0021 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 2026-08-30.
gpt-image-2-skill CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| gpt-image-2-skill CLAUDE.mdWangnov/gpt-image-2-skill | Instructions file | 147 | 5d ago | MIT | A | 536 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |