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.
/plugin marketplace add grainulation/grainulatornpx agentmods add plugins/grainulation/grainulator/marketplacegit clone --depth 1 https://github.com/grainulation/grainulatorGrade A, and why
grainulation-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 2d 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": "grainulation-marketplace",
"owner": {
"name": "Grainulation",
"email": "[email protected]"
},
"metadata": {
"description": "Research sprint tools for Claude Code — structured research with claims, evidence tiers, and compiled output",
"version": "1.0.0"
},
"plugins": [
{
"name": "grainulator",
"source": {
"source": "url",
"url": "https://github.com/grainulation/grainulator.git"
},
"description": "Research sprint orchestrator for Claude Code",
"version": "1.7.1",
"author": {
"name": "Grainulation"
},
"homepage": "https://grainulator.app",
"repository": "https://github.com/grainulation/grainulator",
"license": "MIT",
"keywords": ["research", "wheat", "claims", "evidence", "briefs"],
"category": "research",
"tags": [
"research-sprints",
"analysis",
"documentation",
"decision-making"
]
}
]
}
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.
- 2d ago First seen · 37 lines scan A 8351052e4a93
grainulation-marketplace is a plugin published in the GitHub repository grainulation/grainulator (87 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 2026-08-30.
Other plugins, from other repositories
voltagent-biz
Product, legal, and business specialists - product strategy, licensing, project management, UX research.
claudeblattman
Plugin marketplace listing 1 plugin: starter-kit.
starter-kit
A beginner-friendly desktop-agent workflow: shape rough requests, review plans before acting, and leave handoff notes. Optional second opinions work when Codex or Gemini are already set up.
construction-pm
Create project estimates, change orders, progress reports, and RFI responses for construction project management.
project-manager
AI agent for full-cycle project management: document generation, monitoring, coordination, and scheduled reporting based on PMBoK 8 + Agile hybrid methodology. Covers all 32 PM tasks across 6 project phases — from initiation to closure.
section-508
Expert Section 508 compliance advisor for US federal ICT accessibility — VPAT/ACR completion, WCAG 2.0 AA audits, remediation planning, PDF accessibility, procurement language, keyboard and screen reader testing, undue burden assessments, and agency compliance workflows.