agentmods.dev

ralphctl: Skill for Claude Code

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

changelog-draft is a skill for Claude Code from lukas-grigis/ralphctl. It costs 130 tokens per session (1,061 once invoked), scanned A, original, MIT.

A skill that drafts the `Unreleased` section of ralphctl’s changelog from commits since the latest release tag. It groups changes into Keep a Changelog categories such as Added, Changed, Fixed, and Breaking.

In plain words
What is it for?
Use it before a release or after a batch of merged work to prepare changelog entries and identify internal changes that should be omitted.
Why use it?
It removes the manual work of collecting and sorting recent commits while leaving the user-focused wording and final judgment to the developer.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths.

This is lukas-grigis/ralphctl's own configuration. It tells Claude Code how to work on ralphctl 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 ralphctl configures →

not rated 23repo yesterday A scan SkillSpector: pass 130 tokens original MIT
View source ↗ lukas-grigis/ralphctl npmjs.com
Reuse

Borrowing it

Nothing to install: this file belongs to lukas-grigis/ralphctl. 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/lukas-grigis/ralphctl/main/.claude/skills/changelog-draft/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/lukas-grigis/ralphctl

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-draft

README.md
[![agentmods](https://agentmods.dev/badge/skills/lukas-grigis/ralphctl/changelog-draft.svg)](https://agentmods.dev/skills/lukas-grigis/ralphctl/changelog-draft)
Your own site
<a href="https://agentmods.dev/skills/lukas-grigis/ralphctl/changelog-draft"><img src="https://agentmods.dev/badge/skills/lukas-grigis/ralphctl/changelog-draft.svg" alt="Measured on agentmods" height="20"></a>
Per session 130 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,061 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 $0.00130 $0.01061
Opus 5 $0.00065 $0.00531
Sonnet 5 $0.00026 $0.00212
Haiku 4.5 $0.00013 $0.00106

Measured 7d ago against content hash 9e5663c2d7ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

changelog-draft 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 7d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/draft-changelog.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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-draft/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Changelog Draft

CHANGELOG.md follows Keep a Changelog: a ## [Unreleased] block at the top, then dated ## [X.Y.Z] - YYYY-MM-DD sections, each with ### Breaking / Added / Changed / Fixed / Removed subsections. Populating [Unreleased] by hand means re-reading every commit since the last tag and sorting it by user impact — the kind of blank-page busywork that gets skipped or done sloppily right before a release.

This skill removes the blank page. A script groups the commits mechanically; you do the part that actually matters — turning commit subjects (written for the next developer) into changelog lines (written for the user reading release notes). Those are different audiences, and the gap between them is the whole job.

When this earns its keep

  • Updating CHANGELOG.md, or someone asks "what changed since the last version".
  • Right before a release — run this to fill [Unreleased], then hand off to the release skill which dates it.
  • After a burst of merged work, to capture it while the context is fresh rather than reconstructing it later.

How to run it

  1. Generate the grouped draft:

    bash .claude/skills/changelog-draft/scripts/draft-changelog.sh

    It defaults to commits in <last-tag>..HEAD. Pass an explicit range to override (e.g. v0.11.0..HEAD). It emits ### Breaking / Added / Changed / Fixed / Removed from feat/fix/perf/refactor/!/BREAKING CHANGE, plus an Internal — usually omit bucket (chore/docs/test/ci/build/deps) for you to scan and discard.

  2. Curate — this is the real work, do not skip it. The script's output is raw commit subjects. For each:

    • Rewrite for a user, not the author. fix(tui): root-cause heap-leak — eventbus listeners becomes Fixed a memory leak during long Implement runs. The user does not know what an EventBus listener is.
    • Merge related commits into one line — five feat(tui) commits that built one view are one entry.
    • Drop internal-only churn. Refactors, test changes, doc edits, dep bumps rarely belong in a user changelog — unless one changed observable behaviour. The Internal bucket exists so you check, not so you paste it.
    • Move mis-grouped lines. The script groups by commit type; real impact sometimes differs (a fix that removed a flag belongs in Removed). The Removed placeholder reminds you to scan for these.

Read the full file on GitHub · 63 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. 7d ago First seen · 63 lines · 130 tokens per session scan A 9e5663c2d7ac

Subscribe to this mod's changes

changelog-draft is a skill published in the GitHub repository lukas-grigis/ralphctl (23 stars, last pushed yesterday), licensed MIT. It adds 130 tokens to every session and 1,061 once invoked, about $0.0006 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.

Git and workflowReleasesaianthropicclaudeclicopilotdeveloper-tools
Related

Other skills, from other repositories

pypi-release

This skill should be used when releasing tunacode-cli to PyPI. It keeps the existing local release checks, then hands the actual PyPI upload to a GitHub Actions workflow that uses the repository's PYPIAPITOKEN secret.

alchemiststudiosDOTai/tunacode · 52 tokens

release

Prepare a version release — bump version files, commit, and tag. Just run /release with no arguments.

RockyHong/super-bootstrap · 24 tokens

release-init

Detect project type and generate a tailored project-level /release skill. Run once per project to set up releasing.

RockyHong/super-bootstrap · 25 tokens

github

Full-featured GitHub integration via the gh CLI. Manage repositories, issues, pull requests, CI/CD workflows, releases, and make raw API calls.

aaronboshart1/orionomega · 0 tokens

opensource

Open-source pipeline: fork, sanitize, and package private projects for safe public release. Chains 3 agents (forker, sanitizer, packager). Triggers: '/opensource', 'open source this', 'make this public', 'prepare for open source'.

herakles-dev/opensource-pipeline · 54 tokens

release

Release a new version of the DevoxxGenie IntelliJ plugin — prompt for the target version, bump it in the build files, write a curated CHANGELOG.md entry and plugin.xml change-notes from the git/PR history since the last tag, build to verify, then commit, tag, and publish a matching GitHub release. Use this whenever…

devoxx/DevoxxGenieIDEAPlugin · 121 tokens