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 rsmdt/the-startupnpx agentmods add plugins/rsmdt/the-startup/startgit clone --depth 1 https://github.com/rsmdt/the-startupGrade A, and why
start 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.
What it actually says
{
"name": "start",
"version": "3.8.0",
"description": "Workflow orchestration commands for agentic software development",
"author": {
"name": "Rudolf S."
},
"homepage": "https://github.com/rsmdt/the-startup",
"repository": "https://github.com/rsmdt/the-startup",
"license": "MIT",
"keywords": [
"workflow",
"commands",
"specification",
"implementation",
"refactoring",
"code-review",
"documentation",
"migration"
],
"outputStyles": "./output-styles/"
}
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.
- yesterday First seen · 23 lines scan A 68d03c24b17e
start is a plugin published in the GitHub repository rsmdt/the-startup (511 stars, last pushed 29d 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
aiguide
Plugin marketplace listing 1 plugin: pg.
uk-legal-plugins
UK jurisdiction legal plugins for Claude Code — employment, commercial, corporate, IP, privacy, product, regulatory, AI governance, litigation, law school clinics, and law student tools. All plugins are built for English & Welsh, Scottish, and Northern Irish law.
ai-governance-legal-uk
UK AI governance legal workflows: use case triage against your registry, AI impact assessments across UK regulatory regimes (ICO AI guidance, UK GDPR / DPA 2018, CMA AI guidance, FCA AI requirements, Online Safety Act 2023, DSIT pro-innovation framework, EU AI Act for UK companies selling to the EU). Covers England &…
commercial-legal-uk
Reviews vendor agreements, NDAs, and SaaS subscriptions against your sales-side or purchasing-side playbook under English contract law, tracks renewals and cancel-by deadlines before they're missed, routes escalations to the right approver (including CMA, FCA, and ICO referrals where required), and translates reviews…
corporate-legal-uk
Runs M&A diligence at scale with cited tabular review under English law, builds disclosure letters and closing checklists, drafts board minutes and written resolutions in house format, and tracks entity compliance deadlines under the Companies Act 2006 across England & Wales, Scotland, and Northern Ireland. Covers UK…
employment-legal-uk
Reviews hires and terminations for UK employment law risk flags, classifies workers across the employee/worker/self-employed spectrum, tracks statutory leave deadlines before they're missed, runs internal investigations, and drafts policies with jurisdiction supplements for England & Wales, Scotland, and Northern…