fabro: Skill for Claude Code

.claude/skills/changelog/SKILL.md

changelog is a skill for Claude Code from fabro-sh/fabro. It costs 65 tokens per session (657 once invoked), scanned A, original, MIT.

Instructions for creating product changelog entries in Mintlify, a tool for building documentation websites.

In plain words
What is it for?
Reading git history, grouping relevant changes by date, and writing dated changelog pages in MDX, a Markdown format with components.
Why use it?
It turns recent code changes into user-facing release notes and filters out internal-only work.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

This is fabro-sh/fabro's own configuration. It tells Claude Code how to work on fabro 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 fabro configures →

About the project

Fabro is an open-source system for defining software-development workflows as graphs that AI coding agents execute with verification steps and opportunities for human intervention. Expert engineers and teams use it to coordinate agent tasks, combine models, share version-controlled processes, run agents in isolated sandboxes, and queue work through an API server. The catalogue entries are Fabro-specific skills, instructions, hooks, and settings for working with the system.

fabro-sh/fabro · 1,575 stars · on GitHub · fabro.sh

Reuse

Borrowing it

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

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/fabro-sh/fabro/changelog"><img src="https://agentmods.dev/badge/skills/fabro-sh/fabro/changelog.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 657 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 $0.00065 $0.00657
Opus 5 $0.00032 $0.00329
Sonnet 5 $0.00013 $0.00131
Haiku 4.5 $0.00006 $0.00066

Measured 9d ago against content hash bf46a7f81ba5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

changelog 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 9d 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/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Changelog

Generate user-facing changelog entries from git history and write them as Mintlify MDX files.

Workflow

1. Read watermark

Read .claude/skills/changelog/watermark for the last processed commit SHA. If the file is missing (first run), use the commit from 30 days ago as the starting point: git log --before="30 days ago" --format=%H -1 main.

2. Gather changes

Run git log --oneline --no-merges <watermark>..HEAD to get commits since the watermark. Read commit messages and changed files to understand the actual user-facing impact — don't just reword commit messages.

3. Filter and group by date

Group commits by their commit date (git log --format="%h %ad %s" --date=short). Each date that has user-facing changes gets its own entry file. Dates with only internal changes get no entry.

Include only changes visible to end users:

  • New features and capabilities
  • Bug fixes that affected users
  • Breaking changes or behavioral changes
  • New integrations or provider support
  • Performance improvements users would notice
  • UI/UX changes

Exclude:

  • Internal refactors with no behavior change
  • Test-only changes
  • CI/CD pipeline changes
  • Dependency bumps (unless they fix a user-facing issue)
  • Code style or linting changes

If there are no user-facing changes in the entire range, tell the user and stop.

4. Write changelog entries

Create one file per date at docs/public/changelog/YYYY-MM-DD.mdx, using the commit date (not today's date). If a file already exists for a date, regenerate it with the full set of commits for that day (not just new ones). Follow the references linked above for format, writing style, and hero vs. accordion decisions.

  • Batch related commits into a single feature section (e.g., multiple hook-related commits become one "Lifecycle hooks" section)

Read the full file on GitHub · 61 lines

Files

What ships with it

3 files 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. 9d ago First seen · 61 lines · 65 tokens per session scan A bf46a7f81ba5

Subscribe to this mod's changes

changelog is a skill published in the GitHub repository fabro-sh/fabro (1,575 stars, last pushed 2d ago), licensed MIT. It adds 65 tokens to every session and 657 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 2026-08-30.