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/KSEGIT/Version-SentinelWrote 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/ksegit/version-sentinel/gemini-extension)<a href="https://agentmods.dev/plugins/ksegit/version-sentinel/gemini-extension"><img src="https://agentmods.dev/badge/plugins/ksegit/version-sentinel/gemini-extension/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/ksegit/version-sentinel/gemini-extension"><img src="https://agentmods.dev/badge/plugins/ksegit/version-sentinel/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
version-sentinel 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 3d 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": "version-sentinel",
"version": "0.5.0",
"description": "Hard-blocks dependency additions and version changes until the agent records a WebSearch-verified latest-version check.",
"contextFileName": "GEMINI.md"
}
What ships with it
21 files beside gemini-extension.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.
- assets/hero.html 7.0 KB
- assets/hero.png 351 KB
- assets/logo.svg 7.5 KB
- scripts/auto-record.sh 3.0 KB runs code
- scripts/check-sidecar.sh 2.0 KB runs code
- scripts/check-versions.sh 2.2 KB runs code
- scripts/detect-install-cmd.sh 2.2 KB runs code
- scripts/detect-manifest-edit.sh 5.6 KB runs code
- scripts/lib/circuit-breaker.sh 834 B runs code
- scripts/lib/coalesce.sh 1.6 KB runs code
- scripts/lib/etag-cache.sh 2.9 KB runs code
- scripts/lib/lockfile.sh 3.0 KB runs code
- scripts/lib/options.sh 612 B runs code
- scripts/lib/parse-install-cmd.sh 29 KB runs code
- scripts/lib/parse-manifest.sh 8.5 KB runs code
- scripts/lib/platform.sh 1.0 KB runs code
- scripts/lib/registries.sh 2.0 KB runs code
- scripts/lib/retry.sh 1.3 KB runs code
- scripts/lib/sidecar.sh 4.1 KB runs code
- scripts/prereq-check.sh 1.0 KB runs code
- scripts/vs-record.sh 1.5 KB runs code
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.
- 3d ago Changed 14e1fd972728
- 1mo ago Changed fb4aedd7492b
- 1mo ago First seen · 7 lines scan A 7225f290b8b5
version-sentinel is a plugin published in the GitHub repository KSEGIT/Version-Sentinel (6 stars, last pushed yesterday), 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 2026-09-09.
Other plugins, from other repositories
claude
Intent-to-implementation: from a goal, design docs, notes, or a mix, elicit and validate intent into a grounded 3-doc, then orchestrate dependency-aware parallel execution with right-sized review.
telegram-topics
Telegram channel for Claude Code — 1 project = 1 forum topic, with a live working/idle status badge on each topic. Run multiple projects concurrently, get notifications, and drive or approve sessions remotely from your phone. Configure with /telegram-topics:configure.
magi
Multi-model engineering workflow with MAGI weighted voting and cross-CLI orchestration.
laconic
Brief prose. Short common words. Trust context. State what matters. Omit what reader can infer.
personal-voice-capture
A meta-skill that learns a person's writing voice from their own samples and iterative edits, then compiles it into a durable, reusable voice skill for future agents.
ai-trend-tracker
On-demand AI/ML news, tools, papers, courses, and channel recommendations — always live-searched, never stale.