rove: Skill for Claude Code

.claude/skills/changelog-generator/SKILL.md

changelog-generator is a skill for Claude Code from Sma1lboy/rove. It costs 101 tokens per session (1,597 once invoked), scanned A, original, MIT.

A release-note helper that writes Changeset files for the Rove project. A Changeset is a small Markdown file describing a user-facing change so release scripts can later build the project changelog.

In plain words
What is it for?
Use it when drafting changelogs, release notes, or Changesets, and before preparing a version release. It writes one file per change under the .changeset directory.
Why use it?
It keeps release notes in the source-controlled format expected by Rove instead of requiring manual edits to the generated changelog. It also helps capture changes that were missed earlier.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is Sma1lboy/rove's own configuration. It tells Claude Code how to work on rove itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything rove configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Sma1lboy/rove. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Sma1lboy/rove/main/.claude/skills/changelog-generator/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Sma1lboy/rove

Made for: Claude Code.

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 changelog-generator

README.md
[![agentmods](https://agentmods.dev/badge/skills/sma1lboy/rove/changelog-generator/github.svg)](https://agentmods.dev/skills/sma1lboy/rove/changelog-generator)
Your own site
<a href="https://agentmods.dev/skills/sma1lboy/rove/changelog-generator"><img src="https://agentmods.dev/badge/skills/sma1lboy/rove/changelog-generator/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 changelog-generator

Your own site · 80×15
<a href="https://agentmods.dev/skills/sma1lboy/rove/changelog-generator"><img src="https://agentmods.dev/badge/skills/sma1lboy/rove/changelog-generator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,597 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00101 $0.01597
Opus 5 $0.00051 $0.00798
Sonnet 5 $0.00020 $0.00319
Haiku 4.5 $0.00010 $0.00160

Measured 11d ago against content hash 277472207011, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

changelog-generator 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.

.claude/skills/changelog-generator/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Changelog Generator (Rove)

Drafts release notes as Changesets — one .changeset/<name>.md file per change — in Rove's house style. scripts/release.sh (via changeset version) later consumes them into packages/kobe/CHANGELOG.md and the GitHub release body. See docs/RELEASING.md for the full flow.

When to use

  • The user says "draft changelog", "write release notes", "add a changeset", "what changed since v0.X.Y", or similar.
  • After landing a user-facing change that has no changeset yet (e.g. it was committed before this skill existed, or in a batch that skipped them).
  • Before cutting a release tag — to backfill changesets for anything user-facing that slipped through, so the generated notes are complete.

Rove project conventions (load-bearing)

Every rule in this section overrides the generic guidance further down.

File format — a changeset, not a CHANGELOG edit

  • Do not hand-edit packages/kobe/CHANGELOG.md or invent a ## [Unreleased] section — that file is generated.

  • Each change is a new file .changeset/<two-words-random>.md (the changeset CLI names it; if writing by hand, any unique kebab name works). Shape:

    ---
    "@sma1lboy/rove": patch
    ---
    
    Single-line user-facing summary. This text lands verbatim under the next release and in the GitHub release body.
    
  • The canonical frontmatter bump key is @sma1lboy/rove, with value patch | minor | major.

  • Default to patch for every change, including features and pre-1.0 breaking changes. Use minor or major only when the user explicitly requests that bump in the current turn.

  • The bump type is the category — Changesets groups output under ### Minor Changes / ### Patch Changes automatically. Don't write ### Added/### Fixed headings yourself.

  • One changeset per coherent change. A batch that did three user-visible things → three changesets (or one with three bullets if they're one feature). Prefer the changeset CLI: bun run changeset (interactive) writes the file for you.

Read the full file on GitHub · 95 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. 11d ago First seen · 95 lines · 101 tokens per session scan A 277472207011

Subscribe to this mod's changes

changelog-generator is a skill published in the GitHub repository Sma1lboy/rove (122 stars, last pushed today), licensed MIT. It adds 101 tokens to every session and 1,597 once invoked, about $0.0005 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 2026-08-30.