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.
git clone --depth 1 https://github.com/connerkward/lookdev-auto-skillWrote 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/plugins/connerkward/lookdev-auto-skill/lookdev-auto-skill)<a href="https://agentmods.dev/plugins/connerkward/lookdev-auto-skill/lookdev-auto-skill"><img src="https://agentmods.dev/badge/plugins/connerkward/lookdev-auto-skill/lookdev-auto-skill/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/connerkward/lookdev-auto-skill/lookdev-auto-skill"><img src="https://agentmods.dev/badge/plugins/connerkward/lookdev-auto-skill/lookdev-auto-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
lookdev-auto 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 1mo ago.
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.
What it actually says
{
"name": "lookdev-auto",
"description": "lookdev-auto tunes a visual parameter automatically",
"version": "0.1.0",
"author": {
"name": "Conner K Ward",
"url": "https://github.com/connerkward"
},
"homepage": "https://github.com/connerkward/lookdev-auto-skill",
"repository": "https://github.com/connerkward/lookdev-auto-skill",
"license": "MIT",
"keywords": [
"claude-code",
"claude-skill",
"claude-code-skill",
"agent-skills",
"anthropic",
"vision-model",
"auto-tuning",
"generative-ai",
"evaluation"
]
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 120 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What ships with it
1 file beside plugin.json 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.
- 1mo ago First seen · 24 lines scan A f655f6ec1c3b
lookdev-auto is a plugin published in the GitHub repository connerkward/lookdev-auto-skill (1 stars, last pushed 4mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-31.
Other plugins, from other repositories
context-optimizer
Spend less of your Claude usage on re-reading. In chat: a fresh-start handoff, token checks and prompt sharpening. In Claude Code and Cowork: Haiku 5.5 subagents do the reading and test runs so the expensive model's context stays small, plus read dedup, budget and cache-break warnings, and /cco-audit of your own…
brewtools
Brewtools - Claude Code utilities: text optimization and humanization, secrets scanning, SSH and GitHub Actions deploy, manager hard-wall guard, subagent deadline/return-size/routing guards, task board, context slimming, plugin updates, alternative API providers.
brewcode
Brewcode - Claude Code authoring toolkit: skill, agent and rule creation and sync, semantic code search (semble), project conventions, E2E tests, generated review and domain-team skills, setup dashboard, post-compact plan re-anchor.
skill-creator-plus
Create, test, evaluate, and iteratively improve Claude Code skills with built-in benchmarking, blind A/B comparison, and description optimization.
deep-research
Deep Research (/deep-research or /dr) — exhaustive, evidence-based investigation of any topic. ICD 203 (9/9), GRADE, NIST reproducibility, CRAAP. 89 runs, 85+ domains, 24.3/25 judge score.
zAI-Skills marketplace
Development marketplace for AI-Toolkit, consulting-toolkit, real-estate-investment, career-coach, and plugin-forge plugins.