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/Gekkos-tech/agency-osWrote 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/gekkos-tech/agency-os/agency-core)<a href="https://agentmods.dev/plugins/gekkos-tech/agency-os/agency-core"><img src="https://agentmods.dev/badge/plugins/gekkos-tech/agency-os/agency-core.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
agency-core 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 8d 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": "agency-core",
"description": "Agency project workflow: BRIEF → CONCEPT → DESIGN → BUILD → QA → LAUNCH router, project scaffolding, handoffs and proposals.",
"version": "1.1.0",
"author": {
"name": "GEKKOS Tech",
"url": "https://github.com/gekkos-tech"
},
"homepage": "https://github.com/gekkos-tech/agency-os",
"repository": "https://github.com/gekkos-tech/agency-os",
"license": "MIT",
"keywords": [
"agency",
"workflow",
"project-management",
"web-design"
]
}
What it installs
The manifest is a name and a version. 4 skills, 5 commands travel with it, and installing the plugin installs all of them — 631 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 8d ago First seen · 19 lines scan A c7c85e9fc251
agency-core is a plugin published in the GitHub repository Gekkos-tech/agency-os (5 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
uxcel
UX and product management skills from Uxcel lessons — audits, screens, flows, components, deliverables, processes, and workflows. Use for design reviews, heuristics audits, PRDs, roadmaps, onboarding flows, accessibility, and PM discovery.
product-skills
Product thinking and PM craft. 516 skills and 48 commands across product strategy, discovery, execution, analytics, growth, experience, conversion, and communication.
revenue
Outbound, sales enablement, revenue operations, pricing and packaging, activation, retention, and referrals.
radin
Cost-optimized agentic workflow stack for solo devs: backlog orchestration (radin-orchestrator, radin-plan, radin-review) plus curated companion tools.
scriptorium
An agentic scriptorium for scholarly writing — coordinated AI capabilities (citation audit, reviewer simulation, structural analysis) around shared editorial state.
pmprompt
Claude plugin for product managers: reusable PM skills (PRDs, roadmaps, prioritization, positioning) for Claude Code and Cowork.