OpenDesign is an open-source, local-first desktop app that lets coding agents create prototypes, dashboards, slide decks, images, video, and design systems as exportable files. It is used by people working with agent runtimes such as Claude Code, Codex, Cursor, and DeepSeek Harness. The catalogue add-ons extend the OpenDesign workflow with skills, instructions, commands, and plugins.
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/nexu-io/open-design/diff-reviewnpx skills add nexu-io/open-design --skill diff-reviewgit clone --depth 1 https://github.com/nexu-io/open-designWrote 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/nexu-io/open-design/diff-review)<a href="https://agentmods.dev/skills/nexu-io/open-design/diff-review"><img src="https://agentmods.dev/badge/skills/nexu-io/open-design/diff-review.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 | $0.00039 | $0.00503 |
| Opus 5 | $0.00019 | $0.00251 |
| Sonnet 5 | $0.00008 | $0.00101 |
| Haiku 4.5 | $0.00004 | $0.00050 |
Grade A, and why
diff-review 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 yesterday.
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.
Copies of this mod
2 near-identical copies found in the catalogue:
- diff-review — 88% identical, 4 lines differ
- diff-review — 88% identical, 4 lines differ
What it actually says
Diff review
Spec §20.3 / §21.3.2: a code-migration / tune-collab handoff is worthless without a human-reviewable diff. This atom is the "present the patch, capture the decision" stage.
Inputs
- The project cwd's accumulated edits since the run started (or since the previous diff-review iteration).
plan/steps.jsonfor context per file.
Output
project-cwd/
└── review/
├── diff.patch # unified diff (git apply-shaped)
├── summary.md # human-friendly per-file walkthrough
├── decision.json # { decision: 'accept' | 'reject' | 'partial', accepted_files: [...], rejected_files: [...], reviewer: 'user' | 'agent' }
└── meta.json # { generatedAt, atomDigest, planRevision }
The atom raises a choice GenUI surface with the three top-level
decisions (accept / reject / partial). On partial the user
flips per-file decisions through follow-up surfaces.
Convergence
The atom completes when decision.json has a non-empty decision.
Acceptance writes handoffKind: 'patch' (or 'deployable-app'
when a successful build-test is on file) into the eventual
artifact manifest; rejection rolls back the patch via git restore
or the equivalent in the code-import-bound repo path.
Anti-patterns the prompt fragment forbids
- Skipping the surface and assuming acceptance.
- Generating a
decision.jsonthat lacksaccepted_files/rejected_filesonpartialdecisions. - Rolling back files outside
plan/steps.json's union offiles[]— the patch boundary is a contract.
Status
Implemented by the daemon runner in
apps/daemon/src/plugins/atoms/diff-review.ts, with GenUI decisions persisted
by apps/daemon/src/plugins/atoms/diff-review-genui-bridge.ts.
What ships with it
1 file 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.
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.
- yesterday First seen · 57 lines · 39 tokens per session scan A 46709f440a03
diff-review is a skill published in the GitHub repository nexu-io/open-design (93,861 stars, last pushed today), licensed Apache-2.0. It adds 39 tokens to every session and 503 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 2026-09-03.
Other skills, from other repositories
semantic-commit
Draft a Conventional Commits 1.0.0 message for the AI Atelie repo. Use whenever the user asks to commit, or after staging changes in this repo. Enforces the closed scope set (api|web|mcp|skills|repo|deps), imperative subjects, and a body that reads well in the auto-generated CHANGELOG.md (changelogen + bumpp pipeline).
deck-guizang-editorial
电子杂志 × 电子墨水; 10 个版面 + 5 套调色板 (墨水/靛蓝瓷/森林墨/牛皮纸/沙丘).
deck-open-slide-canvas
锁死 1920×1080 画布, React 组件级自由组合, 不绑模板.
social-spotify-card
Spotify Now Playing 风格卡: 专辑封面 + 进度条 + 播放控制, 适配视频叠加 / 个人主页.
social-x-post-card
拟真 X 推文卡片 + 互动数据 (likes/reposts/views), 适配视频叠加或图卡分享.
video-hyperframes
Hyperframes / Remotion 兼容的连续帧动画, 可自动播放.