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/commands/ksegit/version-sentinel/check-versions)<a href="https://agentmods.dev/commands/ksegit/version-sentinel/check-versions"><img src="https://agentmods.dev/badge/commands/ksegit/version-sentinel/check-versions/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/commands/ksegit/version-sentinel/check-versions"><img src="https://agentmods.dev/badge/commands/ksegit/version-sentinel/check-versions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00019 | $0.00218 |
| Opus 5.5 | $0.00008 | $0.00087 |
| Sonnet 5.5 | $0.00004 | $0.00044 |
| Haiku 4.5 | $0.00002 | $0.00022 |
Grade A, and why
check-versions 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
Use the terminal tool to run bash scripts/check-versions.sh in the workspace root. It scans manifests under the current directory and compares each dependency version to the latest upstream. Supported (v0.1): package.json, requirements*.txt, pyproject.toml, Cargo.toml, *.csproj.
Relay the full output to the user, then interpret it briefly:
- DRIFT rows: current ≠ latest with no
intentional:record. Suggest looking up the latest version and recording it withbash scripts/vs-record.sh <ecosystem> <pkg> <version> <source-url>before bumping. - intentional-pin rows: deliberate pins with a recorded reason — no action needed unless the pin is stale.
- lookup-failed rows: registry fetch failed; suggest re-running once, then checking the registry URL manually.
This audit reports drift without blocking anything.
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 Changed · +3 lines 203f7308100a
- 1mo ago First seen · 12 lines · 19 tokens per session scan A 8a6f58b6ec41
check-versions is a command published in the GitHub repository KSEGIT/Version-Sentinel (6 stars, last pushed 26d ago), licensed MIT. It adds 19 tokens to every session and 218 once invoked, about $0.0001 per session on Opus 5.5. 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 commands, from other repositories
ai-trend-tracker
Ask ai-trend-tracker about AI/ML news, tools, papers, courses, channels, or learning paths — always live-searched and cited.
kickoff
A project-start command that runs product requirements, work breakdown, and design steps in sequence. It can ask decisions at each step or run automatically with --auto.
verify
A verification command that runs a test agent and a code-review agent in the same round, then combines their results.
ship
A delivery command that runs packaging and reporting steps, then bundles the project’s documentation, test results, and built files into an archive.
build-web
A frontend-building command that follows six visible steps: explore, plan, approve, implement, verify, and summarize. It uses project API and product documents as its starting point.
design-execute
A command that turns a design brief into an attachment package and instructions for Claude Design, Figma, or v0, tools used to create interface designs. It then accepts the returned design source for use in a web project.