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/gf-labs/gfl-marketplaceWrote 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/gf-labs/gfl-marketplace/marketplace)<a href="https://agentmods.dev/plugins/gf-labs/gfl-marketplace/marketplace"><img src="https://agentmods.dev/badge/plugins/gf-labs/gfl-marketplace/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/gf-labs/gfl-marketplace/marketplace"><img src="https://agentmods.dev/badge/plugins/gf-labs/gfl-marketplace/marketplace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
gfl-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 10d 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
{
"$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
"name": "gfl-marketplace",
"description": "Greenfield Labs Claude Code plugin marketplace — ramp (adaptive learning) and tools (session lifecycle management)",
"owner": { "name": "Greenfield Labs", "url": "https://github.com/gf-labs" },
"plugins": [
{
"name": "ramp",
"description": "Adaptive learning mode for Claude Code — knowledge graphs, spaced repetition, and passive skill observation",
"source": {
"source": "url",
"url": "https://github.com/gf-labs/ramp.git"
},
"category": "productivity",
"author": { "name": "Bernie Green" }
},
{
"name": "tools",
"description": "Session lifecycle management for Claude Code — orient, checkpoint, archive, and health checks",
"source": {
"source": "url",
"url": "https://github.com/gf-labs/claude-toolbox.git"
},
"category": "productivity",
"author": { "name": "Bernie Green" }
}
]
}
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.
- 10d ago First seen · 29 lines scan A 204072b61b91
gfl-marketplace is a plugin published in the GitHub repository gf-labs/gfl-marketplace (2 stars, last pushed 1mo 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
forge-marketplace
Forge Mentor and related decide-then-code tooling for Claude Code.
recall
Durable, fully-local project memory for Claude Code. Logs every session to .recall/history.md and condenses it into .recall/context.md with a local Python summarizer (TF-IDF + TextRank) — no API key, no external model, nothing leaves your machine. New sessions resume from the saved context.
orchestrator
Token-frugal multi-agent orchestration for Claude Code, built for a Claude Fable 5 chair: Fable plans and decides, Sonnet 5 carries the volume, Opus 5 takes the hard slices and escalations — each worker's effort sized by the chair — and a two-tier verification valve guards the close. When the Fable limit runs dry, an…
go-ultimate
Opinionated Go development skill — architecture, conventions, production readiness, repo/CI hygiene, review, and MCP/agent patterns.
commander-hub marketplace
Plugin marketplace listing 1 plugin: commander.
tg-voice
Transcribe Telegram voice messages using local Whisper (faster-whisper) — automatic PostToolUse hook with setup skill for installation and model download.