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 agentmods add skills/vidhunnan/agentic-skills/version-managernpx skills add vidhunnan/agentic-skills --skill version-managergit clone --depth 1 https://github.com/vidhunnan/agentic-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/vidhunnan/agentic-skills/version-manager)<a href="https://agentmods.dev/skills/vidhunnan/agentic-skills/version-manager"><img src="https://agentmods.dev/badge/skills/vidhunnan/agentic-skills/version-manager.svg" alt="Measured on agentmods" 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 | $0.00173 | $0.04312 |
| Opus 5 | $0.00086 | $0.02156 |
| Sonnet 5 | $0.00035 | $0.00862 |
| Haiku 4.5 | $0.00017 | $0.00431 |
Grade A, and why
version-manager 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.
version-manager
Gives a project one honest answer to four questions: what version is this, what's actually published, what am I testing right now, and what changed between them.
It exists because those four collapse into one number the moment nobody's watching. A local test build bumps the manifest to get a tarball, the manifest is also what the publish step reads, and now the repo's version is ahead of the registry with nothing to say which is true. That is not a hypothetical: it is the drift bug this skill was generalised from, and the fix was structural rather than careful.
Two rules govern everything below:
- Two tracks, never conflated. The released version has exactly one writer. A candidate build carries a suffix that cannot be published and must never move the released number — and if a candidate build has to edit a manifest to produce an artifact, it restores it afterwards, including when the build fails.
- Faithful, never generative. Every version, date and change line comes from git, the manifest, or the registry. A version history is load-bearing precisely because people trust it without checking; a plausible invented row is worse than an empty ledger.
The model
Four ideas, the same for every artifact type:
| The two tracks | released (one writer) vs candidate (X.Y.Z-local.N, -rc.N, a dated draft) |
| The version surface | every file carrying the version — manifest, hardcoded copies, marketplace entries, pinned image tags — and whether they agree |
| The ledger | changelog/VERSION-LOG.md: generated, newest-first, every build and every release, each mapping to the other |
| The profile | which files and which commands, per artifact type — see references/profiles.md |
This skill does not own the changelog. changelog-tracker owns changelog/commits/
and changelog/CHANGELOG.md — what changed, per commit. This one owns
changelog/VERSION-LOG.md only — what shipped, per version. They sit in the same folder
and never write each other's files.
What ships with it
2 files 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.
- 6d ago First seen · 309 lines · 173 tokens per session scan A e711c4efef68
version-manager is a skill published in the GitHub repository vidhunnan/agentic-skills (2 stars, last pushed 6d ago), licensed MIT. It adds 173 tokens to every session and 4,312 once invoked, about $0.0009 per session on Opus 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 skills, from other repositories
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.
updater_guide
Guidance for checking for and installing Row-Bot updates.