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 avizmarlon/agent-skills --skill version-bump-rulesgit clone --depth 1 https://github.com/avizmarlon/agent-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/avizmarlon/agent-skills/version-bump-rules)<a href="https://agentmods.dev/skills/avizmarlon/agent-skills/version-bump-rules"><img src="https://agentmods.dev/badge/skills/avizmarlon/agent-skills/version-bump-rules.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 | $0.00075 | $0.00879 |
| Opus 5 | $0.00037 | $0.00439 |
| Sonnet 5 | $0.00015 | $0.00176 |
| Haiku 4.5 | $0.00007 | $0.00088 |
Grade A, and why
version-bump-rules 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 8d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Version Control — Mandatory Practice
Every software project must maintain a version number. Every change that reaches production or main branch must bump the version in the same commit — no exceptions, no deferral.
Where version lives (by project type)
| Project Type | Version File Location |
|---|---|
| Node.js / npm package | package.json → "version" field |
| WXT (browser extension) | wxt.config.ts → manifest: { version: "x.y.z" } — NOT package.json |
| Monorepo (multiple packages) | each affected package.json + manifest.json if extension |
| Python | pyproject.toml → [project] version OR __version__ in __init__.py |
| Rust / Cargo | Cargo.toml → version field |
| Mobile (Expo) | app.json / app.config.ts → version + buildNumber / versionCode |
| Bash / Python script (standalone) | comment at top: # v1.2.3 |
| Custom setup (no standard file) | VERSION file in root, one line |
Critical: WXT extension gotcha
Browser extensions built with WXT read the version from wxt.config.ts in the manifest block, not from package.json. Bumping only package.json leaves the manifest at the old version, so users see stale version info in the browser extension UI.
Always verify wxt.config.ts when working with WXT projects.
Semantic versioning rules
MAJOR.MINOR.PATCH
│ │ └── bug fix, cosmetic adjustment, refactor with no external impact
│ └──────── new feature, backwards-compatible (new behavior, new UI, new integration)
└─────────────── breaking change (removed behavior, changed public interface, mandatory migration)
When in doubt between MINOR and PATCH? If the end user will notice → MINOR. If only internal code changed → PATCH.
Anti-patterns (mandatory to avoid)
- Committing a new feature without bumping the version → forbidden
- "I'll bump it later" → deferral is not allowed. Bump in the same commit or merge commit
- Version frozen at 0.0.1 while product evolves → traceability failure
- Multiple packages in a monorepo with different versions without justification → align them if they release together
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.
- 8d ago First seen · 65 lines · 75 tokens per session scan A b3c49881aac3
version-bump-rules is a skill published in the GitHub repository avizmarlon/agent-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 75 tokens to every session and 879 once invoked, about $0.0004 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
changelog
Turn a range of commits or merged PRs into a changelog entry grouped by change type. Use when the user asks for release notes, a changelog, or "what changed" between two points.
taiyi-integration
A project workflow skill for closing a TaiyiForge change and recording it in a CHANGELOG.md file. It checks review results, tests, and the state of the working tree before archiving the change.
autoship
Runs a changesets npm release through the version PR, CI publish, and registry verification. Use when asked to "release this package", "autoship", "merge Version Packages", or diagnose a release that did not publish. For feature PRs use pr-creator or pr-babysitter.
graincrawl
Maintain, verify, and release graincrawl, the local-first Granola archive CLI, including SQLite archive behavior, read-only Granola source boundaries, Homebrew tap packaging, and crawlkit-powered TUI/snapshot surfaces.
crawlkit
Maintain and release the crawlkit Go library, preserving downstream compatibility for gitcrawl, slacrawl, discrawl, and notcrawl.
ship
Ship phase. Runs isolated integration test in a fresh worktree, creates a PR with full spec + audit report in the body, watches CI, and auto-fixes failures.