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/choiyounggi/dev-loopWrote 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/choiyounggi/dev-loop/marketplace)<a href="https://agentmods.dev/plugins/choiyounggi/dev-loop/marketplace"><img src="https://agentmods.dev/badge/plugins/choiyounggi/dev-loop/marketplace/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/choiyounggi/dev-loop/marketplace"><img src="https://agentmods.dev/badge/plugins/choiyounggi/dev-loop/marketplace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
dev-loop marketplace 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 today.
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
{
"$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
"name": "dev-loop",
"description": "Marketplace for dev-loop — a wiki-grounded implementation loop plugin for Claude Code (loop-orchestrator + dev-llm-wiki, merged).",
"owner": {
"name": "choiyounggi",
"url": "https://github.com/choiyounggi"
},
"plugins": [
{
"name": "dev-loop",
"description": "Multi-agent orchestration grounded in an LLM wiki. /dev-loop:orchestrate splits one goal into a dependency graph of parallel Claude Code sessions, each in its own worktree, and supervises them natively on Orca (a tracked Task + Dispatch per phase, pushed worker_done / question / escalation events instead of polling, stall detection; raw tmux fallback). Every plan decision must cite a page in a bundled best-practice wiki of 400+ pages across 10 domains, checked by machine gates and a fresh-context plan reviewer, and verified insights from your sessions return as reviewed wiki PRs.",
"category": "development",
"author": {
"name": "choiyounggi",
"url": "https://github.com/choiyounggi"
},
"source": {
"source": "url",
"url": "https://github.com/choiyounggi/dev-loop.git"
},
"homepage": "https://github.com/choiyounggi/dev-loop",
"version": "1.33.0",
"tags": [
"orchestrator",
"verification-loop",
"tdd",
"wiki",
"planning",
"knowledge-base",
"claude-code"
]
}
]
}
The plugins it lists here
This marketplace lists 1 plugin kept in the same repository. Each has its own page, its own measurements and its own install command.
What ships with it
1 file beside marketplace.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.
- today Changed 0eb78403417a
- 2d ago Changed cbf22bd49739
- 4d ago Changed 52c312c73249
- 6d ago Changed c5fb5d253d93
- 7d ago Changed 36711dc930f6
- 9d ago Changed edd3ead89769
- 16d ago Changed 8a8e62887fc4
- 18d ago Changed 13d3b2499dcd
- 24d ago Changed f48722ec1e78
- 28d ago First seen · 36 lines scan A db6ae807579b
dev-loop marketplace is a plugin published in the GitHub repository choiyounggi/dev-loop (6 stars, last pushed yesterday), 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
llm-wiki
Build a shared Markdown knowledge base with local hybrid search and an optional evidence-linked workflow to capture task lessons, evaluate skill improvements, and apply or roll back tested changes.
claude-mega-brain
OKF-powered knowledge context for Claude Code — injects your project knowledge base at every session.
llm-wiki-init
Provides the /llm-wiki-init:wiki-init and /llm-wiki-init:wiki-status commands for scaffolding and inspecting a persistent, LLM-maintained knowledge base on any topic.
kb
Build and maintain LLM-powered knowledge bases as Obsidian wikis with compile, query, lint, and evolve workflows.
plan-cascade
AI-powered cascading development framework with design document system and multi-agent collaboration. Breaks down projects into Features (Mega Plan), Features into Stories (Hybrid Ralph), with auto-generated technical design docs, dependency-driven batch execution, Git Worktree isolation, and support for multiple AI…
project-brain
Every Claude Code session, in every project, captured into one plain-Markdown brain you own. Index-first recall, automatic redaction, LLM-distilled session notes.