Turn scattered reading and half-formed ideas into a design you can defend — a skill, a system, a video script, even the structure of an article. The human adjudicates, the agent runs the errands.
An Agent Skill (Claude Code plugin, works with any SKILL.md-compatible agent): feed it sources and rough ideas as you go — it files and links them, records how your thinking evolves, and assembles the evidence into a system design.
Markdown keeps the record; the canvas makes it readable — every source and idea you add lands on the board, one glance away from any decision's why.
What This Does
- Sources file themselves — drop papers, repos, blog posts; the agent files one card per source, grades it, and anchors every claim to where it came from.
- Ideas are yours alone — only a human creates an idea card; the agent links it to evidence, clusters neighbors, and surfaces conflicts instead of picking a side.
- Output assembles on your word — one command turns surviving ideas into the deliverable, and every later sync runs on your word too; edit output directly and it flows back into ideas.
- Everything is traceable — every design element links back through ideas to the sources that earned it, with an append-only log on every card.
- Plain Markdown, no lock-in — three folders in your repo; versionable, greppable, renders on GitHub. The agent is just the runtime.
- One visual canvas — a self-contained HTML projection of the whole board: no server, no dependencies, rebuilt from the markdown on demand. Commit it, and whoever gets the repo gets the board.
Installation
Claude Code:
/plugin marketplace add tigerless-labs/design-harness
/plugin install design-harness@design-harness
Codex (CLI and the ChatGPT desktop app share one plugin system):
codex plugin marketplace add tigerless-labs/design-harness
then install from /plugins in the CLI or the desktop app's plugin directory.
For other SKILL.md-compatible agents, copy the skill folder into your agent's skill directory:
git clone https://github.com/tigerless-labs/design-harness
cp -r design-harness/plugins/design-harness/skills/design-harness \
~/.claude/skills/
Updating
Claude Code — refresh the marketplace, then update the plugin:
/plugin marketplace update design-harness
/plugin update design-harness@design-harness
(Or enable auto-update for this marketplace under /plugin → Marketplaces.)
Codex — refresh the marketplace snapshot, then update from /plugins:
codex plugin marketplace upgrade
Manual copy — git pull the clone and re-run the cp -r above.
Usage
Talk to your agent in plain language:
> file these papers onto the board
> assemble the design
- Drop material — the agent files and grades each source as a card.
- Think out loud — your judgments land as idea cards, linked to their evidence.
- Say go — the ideas assemble into the output your
target.mddeclares. - Ask for the canvas — the agent builds the board and hands you a clickable link.
Render your own workspace in ten seconds — the demo board is the same projection run on a real workspace:
python3 plugins/design-harness/skills/design-harness/scripts/build_canvas.py \
path/to/your-workspace -o /tmp/canvas
open /tmp/canvas/canvas.html
Share the Why
The board is not just where you think — it's how you show someone else why the design is what it is. The canvas is one self-contained HTML file, so commit it beside your workspace:
python3 plugins/design-harness/skills/design-harness/scripts/build_canvas.py \
path/to/your-workspace -o docs
git add docs/canvas.html
Whoever gets the repo opens one file and gets the whole board — every card one click from the evidence that earned it. Want a URL instead? Serve the same file with hosted pages, the way this repo does.
Canvas Styles
Five skins ship with the canvas; switch live from the toolbar, Pin & Paper is the default. Screenshots below are this repo's own workspace, unretouched — the board view and a close-up for each style.
Pin & Paper (default)
A handmade pinboard: yellow paper ground, ink-blue hand script, pinned notes, taped slips, and dashed hand-drawn threads between them.
Notebook Tabs
Warm ivory stationery: serif italic headings, index cards with colored tab tongues, sticky-note ideas, stitched dashed connections.
Swiss Modern
White, ink, and one red accent: hairline grid, giant grotesk world titles with red ordinals, ruler-straight edges.
BlockFrame
Neo-brutalist pastel decks: thick borders, hard offset shadows, cyan / pink / yellow card blocks that tilt just enough to feel alive.
8-Bit Orbit
A CRT arcade in deep navy — scanlines, neon cyan / yellow / magenta frames, and orthogonal circuit-trace edges. Dark in both color schemes; a CRT has no daylight mode.
Philosophy
- The human adjudicates, the agent runs the errands — agents execute well and judge poorly, and a wrong design costs the whole branch of code built on it.
- Markdown is the only source of truth — every other surface, the canvas included, is a projection: rebuilt wholesale from the markdown, committed and shared or thrown away, never the place facts live.
- Rejected ideas are archived with their reasons, never deleted — six months later, "why didn't we do X?" has an answer.
- Every element of the output must answer "why?" with a link.
This repo is dogfooded on itself: its own design was produced by running the method on ~80 sources about decision-making methods.
License
MIT — vendored renderers (marked, DOMPurify) keep their original headers.