design-loop SKILL.md skillA
This file is byte-identical to the first copy the registry indexed, one of 4 indexed copies. Same content hash, so the same checks give both the same grade.
design-loop from jakeselby/agent-harness is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add jakeselby/agent-harness/design-loop@git:20261006.b2bd78aPins git:20261006.b2bd78a in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- jakeselby/agent-harness
- Path
directory/model-citizen/primitives/skills/design-loop/SKILL.md- Versions recorded
- 3
- Latest version
- git:20261006.b2bd78a, committed Oct 6, 2026
- First version recorded
- Sep 28, 2026
- Size
- 7,876 bytes
- Repository stars
- 24
- License
- MIT
Raise the visual quality of something that renders through a build, screenshot, independent scored critique and fix loop, against rubrics with hard accessibility, design-token, runtime and asset-licensing gates. Use when asked to make a UI, page, HTML doc, dashboard, game scene or 3D asset look dramatically better, more polished or more professional; to improve the visual design, look, styling or visual quality of a surface; to iterate toward a reference, mockup or screenshot; and proactively…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Design loop A closed loop that raises visual quality by measurement rather than taste. The agent that built the thing cannot grade it, so an **independent judge with a clean context** scores each round against a **locked target** until it clears the bar or stalls. Derived from [dream-loop](https://github.com/achimala/dream-loop) (MIT) — see `ATTRIBUTION.md`. **Two standing rules that apply even outside the loop.** Visual work is verified by a capture the agent reads before anything is shown to the user; a claim about how something looks without a capture behind it is unverified. And the look is designed in cheap loops — a mock, a sketch, a throwaway render — before it is engineered into the real pipeline. The loop mechanics are its contribution. The rubrics, hard gates, escalation and asset policy here are ours and differ deliberately; do not reintroduce its asset-sourcing chapter. ## When this is the wrong skill This skill **refines something that already renders**. It needs a running artifact to screenshot. It does not decide what screens exist, what the flows are, or how anything behaves. | If the ask is | Use | | --- | --- | …
Read the whole file at its exact version.
How to install
mdr add jakeselby/agent-harness/design-loop@sha256:6f6ff8546f380c14The line at the top of this page pins the label git:20261006.b2bd78a, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_lowlo4t35z5zkxbz)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Sep 28, 2026 and Oct 6, 2026, about one every 4 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261006.b2bd78a latest | 2026-10-06 | b2bd78a | 7,876 B | A | view · diff |
| git:20260929.1af83d7 | 2026-09-29 | 1af83d7 | 7,877 B | A | view · diff |
| git:20260928.ca93e6d | 2026-09-28 | ca93e6d | 7,835 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (7876 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
jakeselby/agent-harness · 24 stars · license MIT · pushed 2026-10-15 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_lowlo4t35z5zkxbz GET https://markdownregistry.com/api/v1/resolve?ref=jakeselby/agent-harness/design-loop GET https://markdownregistry.com/api/v1/blob/6f6ff8546f380c14a9ac2a2af7369573288e0e6731e6c6feddbf9dc40269edab
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from jakeselby/agent-harness
Every file in jakeselby/agent-harness