autoharness
Autoharness — a self-learning skill layer for Claude Code — distills skills from your real sessions, updates them as you work, and prunes the ones that stop getting used. No daemon, no benchmark.
Feed your agent papers and half-formed ideas — it links them into a system design you can defend. Markdown keeps the record; a visual canvas makes it readable. An Agent Skill for Claude Code & any SKILL.md-compatible agent.
> /plugin marketplace add tigerless-labs/design-harness> /plugin install design-harness@design-harness
What's inside
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.
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/
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.
Talk to your agent in plain language:
> file these papers onto the board
> assemble the design
target.md declares.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
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.
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.
A handmade pinboard: yellow paper ground, ink-blue hand script, pinned notes, taped slips, and dashed hand-drawn threads between them.
Warm ivory stationery: serif italic headings, index cards with colored tab tongues, sticky-note ideas, stitched dashed connections.
White, ink, and one red accent: hairline grid, giant grotesk world titles with red ordinals, ruler-straight edges.
Neo-brutalist pastel decks: thick borders, hard offset shadows, cyan / pink / yellow card blocks that tilt just enough to feel alive.
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.
This repo is dogfooded on itself: its own design was produced by running the method on ~80 sources about decision-making methods.
MIT — vendored renderers (marked, DOMPurify) keep their original headers.
© Tigerless · tigerless.ai · tigerless.com
Autoharness — a self-learning skill layer for Claude Code — distills skills from your real sessions, updates them as you work, and prunes the ones that stop getting used. No daemon, no benchmark.
FAQ
design-harness is a Claude Code plugin with 1 hand-picked skill for documentation work, indexed on Flowy. Install it with the command on its page. It includes design-harness. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.
Is this plugin yours?
Claim it with GitHubSubmit a pluginPromote it