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/prime-radiant-inc/prime-radiant-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/prime-radiant-inc/prime-radiant-marketplace/marketplace)<a href="https://agentmods.dev/plugins/prime-radiant-inc/prime-radiant-marketplace/marketplace"><img src="https://agentmods.dev/badge/plugins/prime-radiant-inc/prime-radiant-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/prime-radiant-inc/prime-radiant-marketplace/marketplace"><img src="https://agentmods.dev/badge/plugins/prime-radiant-inc/prime-radiant-marketplace/marketplace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
prime-radiant-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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "prime-radiant-marketplace",
"description": "Prime Radiant's Claude Code plugin marketplace.",
"owner": {
"name": "Prime Radiant, Inc.",
"email": "[email protected]"
},
"plugins": [
{
"name": "shepherd-pr",
"description": "Shepherd GitHub pull requests through CI and review.",
"source": {
"source": "github",
"repo": "prime-radiant-inc/shepherd-pr"
},
"author": {
"name": "Prime Radiant, Inc."
}
},
{
"name": "iterative-development",
"description": "An iterative implementation methodology that pairs with superpowers. Extracts requirements with proof obligations from large spec collateral, defines a walking skeleton that closes a real journey, then loops through audited sprints building a behavior evidence corpus until an auditor confirms the product matches the spec.",
"source": {
"source": "github",
"repo": "prime-radiant-inc/iterative-development"
},
"author": {
"name": "Prime Radiant, Inc.",
"email": "[email protected]"
}
},
{
"name": "greenfield",
"description": "Reverse engineer clean behavioral specs from any codebase.",
"source": {
"source": "github",
"repo": "prime-radiant-inc/greenfield"
},
"author": {
"name": "Prime Radiant, Inc."
}
},
{
"name": "study-skills",
"description": "Skills for durable agent learning across sessions: analytical reading that produces artifacts, a cross-linked Zettelkasten slip-box with a bundled CLI, first-person beliefs with falsifiers and revision logs, mid-task experience capture with conservative synthesis, a four-test gate for distilling new skills, and read-only deliberation forks at high-stakes decision points.",
"source": {
"source": "github",
"repo": "prime-radiant-inc/study-skills"
},
"author": {
"name": "Prime Radiant, IWhat 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.
- yesterday Changed · +11 lines a6ddda96696f
- 3d ago Changed · +12 lines 80ab04accd9a
- 12d ago First seen · 34 lines scan A d122d480d626
prime-radiant-marketplace is a plugin published in the GitHub repository prime-radiant-inc/prime-radiant-marketplace (4 stars, last pushed 2d ago), licensed Apache-2.0. 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
planning
Structured implementation planning, interactive annotation review, and autonomous plan execution.
workflow
Session workflow helpers and deferred-work backlog - knowledge capture, confusion handling, course correction, clipboard copy, backlog items.
brainstorm
Collaborative design dialogue - idea to approaches to design to plan.
release-tools
Release workflow tools - auto-versioning, release notes, changelog updates.
review
PR review, interactive git diff annotation review, and writing style guide.
thinking-tools
Analytical thinking tools - dialectic analysis, bias elimination, codex consultation.