semver-bump-decider

semver-bump-decider is a skill for Claude Code, Codex from samuelgudi/iknowkungfu. It costs 63 tokens per session (1,400 once invoked), scanned A, original, MIT.

A checklist for choosing the next version of a library that follows Semantic Versioning, where version changes communicate compatibility: major for breaking changes, minor for additions, and patch for fixes.

In plain words
What is it for?
Use it to decide a release number from commits, pull requests, or a changelog, and to review whether a change breaks existing users.
Why use it?
It reduces the chance of missing breaking changes or applying the wrong versioning rule, including for libraries before version 1.0.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to decide a release number from commits, pull requests, or a changelog, and to review whether a change breaks existing users.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/samuelgudi/iknowkungfu/semver-bump-decider
Install

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.

Any agent
npx skills add samuelgudi/iknowkungfu --skill semver-bump-decider
Clone the repo
git clone --depth 1 https://github.com/samuelgudi/iknowkungfu

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for semver-bump-decider

README.md
[![agentmods](https://agentmods.dev/badge/skills/samuelgudi/iknowkungfu/semver-bump-decider/github.svg)](https://agentmods.dev/skills/samuelgudi/iknowkungfu/semver-bump-decider)
Your own site
<a href="https://agentmods.dev/skills/samuelgudi/iknowkungfu/semver-bump-decider"><img src="https://agentmods.dev/badge/skills/samuelgudi/iknowkungfu/semver-bump-decider/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.

agentmods 80×15 button for semver-bump-decider

Your own site · 80×15
<a href="https://agentmods.dev/skills/samuelgudi/iknowkungfu/semver-bump-decider"><img src="https://agentmods.dev/badge/skills/samuelgudi/iknowkungfu/semver-bump-decider.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,400 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00063 $0.01400
Opus 5 $0.00032 $0.00700
Sonnet 5 $0.00013 $0.00280
Haiku 4.5 $0.00006 $0.00140

Measured 11d ago against content hash 581ba3cb899d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

semver-bump-decider 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 11d 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.

skills/samuelgudi/semver-bump-decider/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

semver-bump-decider

A decision aid for picking the next version number under Semantic Versioning 2.0.0. The rule is short ("MAJOR for breaking, MINOR for additive, PATCH for fixes"); the application is where people slip.

Use this skill when

  • You have a list of changes (commits, PRs, a CHANGELOG draft) since the last release and need to choose the next version.
  • A reviewer asks "is this a breaking change?" and you want a structured answer, not a gut feeling.
  • You are maintaining a 0.x library and need to apply the relaxed pre-1.0 rules correctly.

Decision rule

Apply in order. The first match wins.

  1. MAJOR — any of:
    • A public symbol (function, class, type, exported field) was removed or renamed.
    • A public function's signature was changed in a non-additive way (required parameter added, parameter type narrowed, return type changed in a way callers can observe).
    • Default behaviour changed for an existing input (same call now returns different result, throws where it didn't, or has different side effects).
    • An advertised guarantee was weakened (e.g. a previously-stable order is no longer guaranteed, a previously-idempotent call is no longer idempotent).
    • The minimum supported runtime/language version was raised.
    • A previously-deprecated symbol was removed.
    • A configuration default flipped.
  2. MINOR — none of the MAJOR conditions, and any of:
    • A new public symbol was added.
    • A new optional parameter was added with a back-compatible default.
    • A new field was added to a returned object (and consumers were not told to treat the object as closed).
    • A deprecation warning was added on an existing symbol (the symbol still works).
    • A new optional configuration knob was introduced with a back-compatible default.
  3. PATCH — none of the above, only:
    • Bug fixes that restore documented behaviour.
    • Performance improvements that do not change observable behaviour.
    • Internal refactors, dependency bumps that don't surface in the public API, documentation, comment, or typo fixes.

Read the full file on GitHub · 84 lines

Files

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.

Changes

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.

  1. 11d ago First seen · 84 lines · 63 tokens per session scan A 581ba3cb899d

Subscribe to this mod's changes

semver-bump-decider is a skill published in the GitHub repository samuelgudi/iknowkungfu (2 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 1,400 once invoked, about $0.0003 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.