Skip to content
Back to search

devfast

MarketplaceWorks with Claude CodeGitHub

open-source canvas for thoughtful software design

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked yesterday

Check it deeper on your machine

It has changed since its scan on 18 Nov 2026. Its scripts were only partly scanned.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/devdotfast/whiteboard with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/devdotfast/whiteboard'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/devdotfast--whiteboard/badge.svg)](/listings/devdotfast--whiteboard)

HTML

<a href="/listings/devdotfast--whiteboard"><img src="/api/listings/devdotfast--whiteboard/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

1. [Download Whiteboard](https://dev.fast/install) and open the app. On macOS you can also run `brew install --cask devdotfast/tap/whiteboard`. 2. Connect Claude Code, Codex, or another coding agent from the welcome screen. 3. Ask your agent to review your current branch against up-to-date main and open the result in Whiteboard.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 16 lines
  1. {
  2. "name": "devfast",
  3. "owner": { "name": "dev.fast" },
  4. "plugins": [
  5. {
  6. "name": "whiteboard",
  7. "source": "./packages/agent-plugins/claude",
  8. "description": "Connect your agent to dev.fast Whiteboard"
  9. },
  10. {
  11. "name": "diffr",
  12. "source": "./diffr/packages/claude-code/plugin",
  13. "description": "Review diffs with diffr in a pane"
  14. }
  15. ]
  16. }
README.md · README · 135 lines
  1. <div align="center">
  2. <img
  3. src="docs/assets/review-logo.png"
  4. width="96"
  5. alt="Whiteboard logo"
  6. />
  7. <h1>Whiteboard</h1>
  8. <p><strong>an open-source canvas for thoughtful software design</strong></p>
  9. <p>
  10. <a href="https://dev.fast/install">Download for macOS, Windows, and Linux</a> ·
  11. <a href="https://dev.fast">Website</a> ·
  12. <a href="https://github.com/devdotfast/whiteboard/wiki/Roadmap">Roadmap</a> ·
  13. <a href="https://discord.gg/wYvd2cpMQg">Discord</a>
  14. </p>
  15. <p>
  16. <a href="https://news.ycombinator.com/item?id=49833867"><img src="https://hackergit.org/badge/devdotfast/whiteboard.svg?style=rank" alt="Hacker News" width="250" height="55"></a>
  17. </p>
  18. </div>
  19. Whiteboard is an open-source desktop app where humans and agents can architect software together in a common workspace.
  20. Whiteboard plugs into the tools you already use - e.g. Claude Code, Codex, etc. – and gives your agent an SDK to draw on an in-app canvas to describe its work.
  21. <p align="center">
  22. <img
  23. src=".github/assets/whiteboard-demo.gif"
  24. width="880"
  25. alt="An agent writes a Whiteboard review from a terminal prompt, which includes a sequence diagram and a call tree"
  26. />
  27. </p>
  28. Here’s a 1 min demo video explaining more: https://www.youtube.com/watch?v=ChPn3ftULWE
  29. ## Quickstart
  30. 1. [Download Whiteboard](https://dev.fast/install) and open the app. On macOS
  31. you can also run `brew install --cask devdotfast/tap/whiteboard`.
  32. 2. Connect Claude Code, Codex, or another coding agent from the welcome screen.
  33. 3. Ask your agent to review your current branch against up-to-date main and
  34. open the result in Whiteboard.
  35. ## Guidance
  36. In our experience, Whiteboard works best with models like GPT-6 Sol and Claude Opus 5.5 for their intelligence, cost, and speed tradeoff.
  37. Here are a few example prompts of how to use Whiteboard effectively. We are working hard to make sure the right choices are baked in by default to the system prompt - part of why this system is open source! - but in the meantime:
  38. ### For a new API change
  39. > hey, this stack of commits is set up so i can get an [api] to do [objective]
  40. >
  41. > i'd like to see:
  42. >
  43. > - proposed api
  44. > - examples
  45. > - motivations for this (if available to you in context/in the repo)
  46. >
  47. > and then we can dive into implementation + explaining how things worked.
  48. ### For a change to add telemetry:
  49. > Can you explain to me the telemetry changes from the newest posthog pr https://github.com/devdotfast/whiteboard/commit/4837e107946e27ebad50c282eb0f2585210d2a35 -- what are we tracking, how can we build good dashboards or product waterfalls from it? what do we do for hangs, errors, crashes etc... use whiteboard
  50. If you see anything you don't like, highlight it in your clipboard and give it your agent, and it can re-draw on the Whiteboard to suit your needs!
  51. ## Why does this exist?
  52. ### Diagrams that lead to code
  53. Pure HTML tools didn’t provide easy affordances to connect a spec or diagram to code; this is especially tricky since tradeoffs are often only discovered after a first pass at implementation. In Whiteboard, when you click on visualizations like a sequence diagram, an entity relationship diagram, or a quote from the agent’s trace, you can jump to the underlying code directly. When navigating code, you get keybindings and LSP support from VSCode out of the box.
  54. ### Semantic diff viewer
  55. Raw diff views can be very noisy, so we wrote a semantic, AST-aware diff viewer in Rust so you can only view the code changes which are relevant to you. We’ve set up some sane defaults: large added functions are summarized as pseudocode, and things like unit tests and documentation changes are collapsed / hidden. This is all customizable with a WASM-based plugin system.
  56. ### Decision log
  57. We found it difficult to reason about what set of decisions our agents made autonomously & how that impacts a change. So we built tools for agents to query and link their own traces on the Whiteboard, so you can visualize the requirements that you set, understand how they were implemented, and understand what decisions the agent made autonomously.
  58. ## Open source, on your machine
  59. Whiteboard is MIT-licensed and runs against your local checkouts. A hosted
  60. product for teams is planned, and everything will always remain self-hostable.
  61. ## Known limitations
  62. - You cannot currently edit files in Whiteboard. If this is something that you find yourself wanting to do, please file an issue!
  63. - Working and browsing files across multiple repos in a single review isn't well supported.
  64. - While you can share reviews between machines with the share button, updates made after a review is shared don't appear for others. You would need to re-share the review.
  65. ## Contributing
  66. Contributions and feedback are welcome.
  67. Read [CONTRIBUTING.md](CONTRIBUTING.md) for setup and the pull request workflow,
  68. and follow the [Code of Conduct](CODE_OF_CONDUCT.md). Report vulnerabilities as
  69. described in [SECURITY.md](SECURITY.md). Questions? Ask on
  70. [Discord](https://discord.gg/wYvd2cpMQg).
  71. ## Privacy
  72. Whiteboard runs against local checkouts. Anonymous telemetry does not include
  73. your code, diffs, Whiteboard text, prompts, or model output. Read the
  74. [privacy overview](docs/privacy.md), inspect the complete
  75. [telemetry reference](docs/telemetry.md), or turn telemetry off at any time.
  76. ## License
  77. Whiteboard is available under the [MIT License](LICENSE). The vendored Code -
  78. OSS fork retains Microsoft's MIT license and third-party notices; see
  79. [`apps/review-desktop/LICENSE`](apps/review-desktop/LICENSE) and
  80. [`apps/review-desktop/UPSTREAM`](apps/review-desktop/UPSTREAM).
  81. ## On vendoring Code OSS
  82. With everyone using dedicated agent TUIs and desktop apps, we only use our text editors for reviewing line-by-line diffs now, so we figured why not have a text editor meant for reviewing code. In that case, might as well start off with the most successful open source editor out there as a baseline.
  83. We vendor Code OSS unlike other forks that maintain patches because coding agents have a hard time with patches and there's a lot of stuff from stock VS Code (i.e., ~45% of the codebase is Copilot these days 😬) that we don't need.
  84. We regularly monitor upstream Code OSS and merge in security/feature patches as they come in.
  85. ## Influences
  86. - <https://www.geoffreylitt.com/2026/07/02/understanding-is-the-new-bottleneck>
  87. — a great overview of the constraints of modern software engineering.
  88. - <https://maggieappleton.com/2025-08-vibe-legacy-code/> and
  89. <https://blog.val.town/vibe-code> — do a great job describing how AI-generated
  90. code fits into the pre-2025 notion of software engineering.
  91. - Karpathy on agents:
  92. - On LLM agents: <https://x.com/karpathy/status/1979644538185752935>
  93. - On agents as "junior engineer savants":
  94. <https://x.com/karpathy/status/1915581920022585597>

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.