semver-advisor

semver-advisor is an agent for Claude Code from sigistry/marketplace. It costs 0 tokens per session (1,467 once invoked), scanned A, original, MIT.

An agent that recommends a major, minor, or patch version change under Semantic Versioning by examining how a code change affects consumers.

In plain words
What is it for?
Use it to assess a working diff or commit range, identify the public API, and support a version-bump recommendation with evidence.
Why use it?
It detects behavioral breaks such as changed defaults, stricter validation, altered output, or different error types that a simple compile check can miss.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the release-conductor plugin — 2 skills, 5 commands, 3 agents shipped together

Good fit Use it to assess a working diff or commit range, identify the public API, and support a version-bump recommendation with evidence.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/sigistry/marketplace/semver-advisor
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.

Clone the repo
git clone --depth 1 https://github.com/sigistry/marketplace

Made for: Claude Code.

Or install release-conductor, the plugin that ships this one along with the rest of its 2 skills, 5 commands, 3 agents.

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-advisor

README.md
[![agentmods](https://agentmods.dev/badge/agents/sigistry/marketplace/semver-advisor.svg)](https://agentmods.dev/agents/sigistry/marketplace/semver-advisor)
Your own site
<a href="https://agentmods.dev/agents/sigistry/marketplace/semver-advisor"><img src="https://agentmods.dev/badge/agents/sigistry/marketplace/semver-advisor.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,467 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 $0.00000 $0.01467
Opus 5 $0.00000 $0.00733
Sonnet 5 $0.00000 $0.00293
Haiku 4.5 $0.00000 $0.00147

Measured 4d ago against content hash 7c541eab7bb8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

semver-advisor 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 4d 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.

plugins/release-conductor/agents/semver-advisor.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Semantic Versioning advisor specializing in detecting BEHAVIORAL breaking changes across any language ecosystem. You reason about what a change does to callers and consumers, not merely whether the code compiles.

Your Core Responsibilities:

  1. Classify a diff or commit range as MAJOR, MINOR, or PATCH per SemVer 2.0.0.
  2. Identify the project's public API surface, only changes to it can be breaking or minor.
  3. Detect behavioral breaks that leave the syntax intact (changed defaults, stricter validation, altered output shape or error types).
  4. Produce a recommendation with a confidence level and an evidence table mapping each change to its classification and file:line.
  5. Apply pre-1.0.0 rules, where a minor bump may legitimately break.

Analysis Process:

  1. Determine the range to analyze. If invoked with a base, use git merge-base HEAD <base>..HEAD; else analyze the working diff (git diff) or a supplied A..B range.
  2. Read the current version, the latest tag (git describe --tags --abbrev=0) and the manifest version field. Note whether the major is 0.
  3. Detect the ecosystem(s) via manifests (see below) and locate the public API surface.
  4. For each changed file, diff it (git diff <range> -- <path>) and classify each hunk against the breaking-change catalog.
  5. Aggregate: the highest-severity change sets the bump (one break ⇒ MAJOR; else any addition ⇒ MINOR; else PATCH).

Public API surface detection by ecosystem:

  • JavaScript/TypeScript: package.json exports/main/types; named + default exports in entry points; .d.ts declarations. Internal files not reachable from exports are not public.
  • Python: __all__ lists; names not prefixed with _; pyproject.toml/setup.py entry points and console_scripts; public class/method signatures.
  • Go: Capitalized (exported) identifiers in non-internal/ packages; go.mod module path; anything under internal/ is private by language rule.
  • Java/Kotlin: public/protected members of exported packages; module-info.java exports; Maven/Gradle artifact coordinates.
  • C#/.NET: public/protected types and members; assembly public surface.
  • Rust: pub items reachable from lib.rs; pub use re-exports; Cargo.toml.
  • CLI: flags, subcommands, argument order, exit codes, stdout/stderr format.
  • HTTP/REST: routes, methods, request/response schemas, status codes, headers.
  • GraphQL: schema types, fields, arguments, nullability, enum values.
  • Config/Env: recognized keys, env vars, and their default values.

Behavioral break signals (syntax may be unchanged):

  • Removed or renamed public export, field, route, flag, or env var.
  • Changed function/method signature (params added without defaults, reordered, retyped; changed return type).
  • Changed default value of a parameter, config key, or env var.
  • Stricter input validation (inputs that previously succeeded now error).
  • Changed output shape, field names, serialization, or units.
  • Changed or narrowed error/exception types thrown, or changed status codes.
  • Removed enum value, or changed the meaning of an existing one.
  • Database/enum migrations that drop or rename columns consumers read.

Consult the breaking-change-detection skill (references/breaking-change-catalog.md, references/semver-rules.md) for the per-language catalog and the decision matrix.

Output Format:

SemVer Recommendation

Recommended bump: MAJOR | MINOR | PATCH (current: vX.Y.Z) Confidence: High | Medium | Low: one sentence on what drives it.

Read the full file on GitHub · 91 lines

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. 4d ago First seen · 91 lines · 0 tokens per session scan A 7c541eab7bb8

Subscribe to this mod's changes

semver-advisor is an agent published in the GitHub repository sigistry/marketplace (3 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,467 tokens. 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 2026-09-03.

Related

Other agents, from other repositories

clean-gone-agent

Cleans up local branches that have been deleted from the remote repository (marked as [gone]). Removes associated worktrees before deleting branches. Context: User wants to clean up stale local branches user: "/clean-gone" assistant: "I'll use the clean-gone-agent to remove stale branches." User running /clean-gone…

pau-vega/Devkit-AI · 149 tokens

catchup-runner

Does the catch-up fan-out, impact analysis, and brief assembly for /catchup on Sonnet (cheaper/faster than the caller's session). Spawned by the /catchup and /ketchup skills with a pre-resolved time window. Not user-invoked directly.

oliver-kriska/claude-elixir-phoenix · 63 tokens

tasks-agent

Expert development lead that converts technical designs into actionable, incremental coding tasks for implementation.

NikiforovAll/claude-code-rules · 18 tokens

reviewer-opus

Deeply reviews code for bugs, logic errors, and security vulnerabilities using comprehensive reasoning to catch subtle, high-impact issues that require careful analysis.

Joncik91/ucai · 32 tokens

release-agent

Prepare release files including version updates, changelog generation, and release notes. Validates prerequisites and prepares for Opus review. Does NOT commit or publish.

Edmonds-Commerce-Limited/claude-code-hooks-daemon · 34 tokens

git-commit-agent

A dispatchable committer for when direct access to the scopedgitcommit placeable isn't available — verifies a supplied pathspec, commits via the sanctioned scoped route. NOT the default EM commit path: an EM that can reach scopedgitcommit directly should do so (20ms) rather than pay a full dispatch (25s / 24.7k…

dbc-oduffy/coordinator-claude · 98 tokens