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/katareayush/video-captionsWrote 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/katareayush/video-captions/seedgen)<a href="https://agentmods.dev/plugins/katareayush/video-captions/seedgen"><img src="https://agentmods.dev/badge/plugins/katareayush/video-captions/seedgen/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/katareayush/video-captions/seedgen"><img src="https://agentmods.dev/badge/plugins/katareayush/video-captions/seedgen.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
seedgen 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 1mo 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": "seedgen",
"displayName": "Seedgen",
"version": "0.1.0",
"description": "Analyze any repo and generate a runnable, schema-aware test-data seed script. Works across web2, web3, Python, and more, with locale/filter support.",
"author": {
"name": "katareayush",
"email": "[email protected]"
},
"keywords": ["test-data", "seed", "fixtures", "database", "web3", "faker"],
"homepage": "https://seedgen.katareayush.com",
"repository": "https://github.com/katareayush/video-captions",
"license": "MIT"
}
What it installs
The manifest is a name and a version. 1 skill, 1 command travel with it, and installing the plugin installs all of them — 145 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.
- 1mo ago First seen · 15 lines scan A 3e701f119fc3
seedgen is a plugin published in the GitHub repository katareayush/video-captions (9 stars, last pushed 2mo 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
looptimal
Turns an objective into a delivered, VERIFIED OUTCOME: frames a hash-pinned sealed acceptance suite, designs the right loop (the loop-design wizard, formerly LoopPrint), war-games it forward, executes with dynamic domain-expert sub-agents (maker != checker), and gates completion on a separate verifier re-running the…
craft
Engineering standards for any code work on any stack — writing production code, slicing and reviewing PRs, authoring tests, running gates, merging, and running agent fleets.
preflight-security-audit
Comprehensive 360 pre-ship audit: 61 checks across security, reliability, performance, AI/LLM, privacy/compliance, and launch readiness — including live-database, serverless/edge, GraphQL, client-side, and modern-attack (Trojan Source) checks. Reports a 0–100 security score with severity-ranked findings and proposes…
markifact marketplace
Run Google Ads, Meta Ads, GA4, Shopify, and 50+ more platforms from Claude. 1000+ operations with human-in-the-loop on every write.
craft
Full-stack developer toolkit with integrated workflow automation - 48 commands, 2 agents, 41 skills with standardized dry-run preview mode (29 with --dry-run support). Code, git, site, docs, testing, architecture, CI, distribution, teaching workflows, planning, release pipeline, and ADHD-friendly features including…
neatcontext
Save Claude Code work as reusable, domain-aware context.