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.
npx skills add Smirnov-Labs/claude-skills --skill finding-latest-versionsgit clone --depth 1 https://github.com/Smirnov-Labs/claude-skillsWrote 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/skills/smirnov-labs/claude-skills/finding-latest-versions)<a href="https://agentmods.dev/skills/smirnov-labs/claude-skills/finding-latest-versions"><img src="https://agentmods.dev/badge/skills/smirnov-labs/claude-skills/finding-latest-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/skills/smirnov-labs/claude-skills/finding-latest-versions"><img src="https://agentmods.dev/badge/skills/smirnov-labs/claude-skills/finding-latest-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 | $0.00087 | $0.00950 |
| Opus 5.5 | $0.00035 | $0.00380 |
| Sonnet 5.5 | $0.00017 | $0.00190 |
| Haiku 4.5 | $0.00009 | $0.00095 |
Grade A, and why
finding-latest-versions scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Finding latest versions
latest-version (in this skill's bin/) prints the newest version of a GitHub repo or a container image. It sorts tags as versions, skips pre-releases unless you ask, and reads past the first page.
Do not look versions up by hand. GitHub's releases/latest picks by date, so a backport can win. Registries list tags in text order, a page at a time. So 1.9 comes after 1.10, and the newest can be on the last page.
| You need | Run |
|---|---|
| The newest release of a GitHub repo | latest-version cloudflare/cloudflared |
| The 3 newest tags of an image | latest-version docker.io/library/caddy -n 3 |
| A tag on any other registry | latest-version ghcr.io/project-zot/zot |
| The newest of one line | latest-version kubernetes/kubernetes --match '^v1\.31\.' |
| The newest variant of an image | latest-version caddy --match '-alpine$' |
| Pre-releases too | latest-version prometheus/prometheus --pre |
Tags with a prefix, such as jq-1.8.2 |
latest-version jqlang/jq --match '^jq-(.+)$' |
| The digest, to pin an image | latest-version registry.k8s.io/pause --digest 3.10.2 |
| All fields, for a script | add --json |
With a gh login, GitHub calls send gh's token, else they use the public API (60 calls an hour). latest-version --help lists every flag.
Reading the output
The output is one tag per line, newest first, as the source spells it.
| Exit | Meaning | Do |
|---|---|---|
| 0 | found | use the first line |
| 1 | nothing matched | read stderr: it says what it set aside |
| 2 | network or API error | read stderr: a rate limit, a private image, an unknown repo, or a list it cannot read in full |
| 3 | usage error | correct the command |
--digest prints sha256:..., for a multi-platform image the digest of the index, which docker pull uses.
How tags sort:
1.10is newer than1.9. Avprefix does not count.- A suffix such as
-rc.1,-betaora1makes a pre-release, shown only with--pre. - Any other suffix (
-alpine,-slim,-1) makes a variant, shown only with--match. Release words (.Final,-lts) do not count as a suffix. - Tags that are not versions (
latest,main,sha-...) are set aside. - A one-number tag such as
2or20241105counts only with--match. 13.3and13.3.0are one version. The longer tag prints;--jsonlists the other underaliases.
What ships with it
1 file beside SKILL.md 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.
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 · 54 lines · 87 tokens per session scan A 4665c46a36ce
finding-latest-versions is a skill published in the GitHub repository Smirnov-Labs/claude-skills (6 stars, last pushed yesterday), licensed MIT. It adds 87 tokens to every session and 950 once invoked, about $0.0003 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 2026-11-07.
finding-latest-versions compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| finding-latest-versionsSmirnov-Labs/claude-skills | Skill | 6 | yesterday | MIT | A | 87 | Claude Code, Codex |
| deploy-akashickachofugetsu09/akashic-agent | Skill | 519 | yesterday | MIT | A | 38 | Claude Code, Codex |
| releasememgraph/ai-toolkit | Skill | 119 | yesterday | MIT | A | 35 | Claude Code, Codex |
| single-host-deployhxy91819/mason-skills | Skill | 3 | today | MIT | B | 52 | Claude Code, Codex |
| deployment-operationszhpeng24/devkit | Skill | 3 | 3mo ago | MIT | A | 57 | Claude Code, Codex |
| ferrogate-releaselianluo-esign/ferrogate | Skill | 31 | 1mo ago | none | A | 88 | Claude Code, Codex |
| release-and-publishcyanheads/orcid-mcp-server | Skill | 6 | 11d ago | Apache-2.0 | A | 155 | Claude Code |