changelog-writer

changelog-writer is a skill for Claude Code, Codex from migmcc/agent-skill-quality-gate. It costs 26 tokens per session (357 once invoked), scanned A, original, MIT.

A release-note writer that turns merged pull requests into a Markdown section for a changelog. A changelog is a record of what changed in each software release.

In plain words
What is it for?
Use it when preparing a release from pull request titles, numbers, and a supplied version number.
Why use it?
It saves time summarising completed work and keeps features, bug fixes, and documentation changes organised.

Skill for Claude CodeCodex

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

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.

agentmods
npx agentmods add skills/migmcc/agent-skill-quality-gate/good-skill
Any agent
npx skills add migmcc/agent-skill-quality-gate --skill good-skill
Clone the repo
git clone --depth 1 https://github.com/migmcc/agent-skill-quality-gate

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 changelog-writer

README.md
[![agentmods](https://agentmods.dev/badge/skills/migmcc/agent-skill-quality-gate/good-skill.svg)](https://agentmods.dev/skills/migmcc/agent-skill-quality-gate/good-skill)
Your own site
<a href="https://agentmods.dev/skills/migmcc/agent-skill-quality-gate/good-skill"><img src="https://agentmods.dev/badge/skills/migmcc/agent-skill-quality-gate/good-skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 357 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00026 $0.00357
Opus 5 $0.00013 $0.00179
Sonnet 5 $0.00005 $0.00071
Haiku 4.5 $0.00003 $0.00036

Measured 5d ago against content hash 0cf118a87181, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

changelog-writer 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 5d 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.

examples/good-skill/SKILL.md · 57 lines

What it actually says

changelog-writer

Purpose

Generate a clear, human-readable changelog entry for a release from a list of merged pull requests, grouped by change type (features, fixes, docs).

When to use

Use this skill when preparing a release and you have a list of merged PRs that need to be summarized into release notes. Do not use it to decide version numbers — that is the release-manager's job.

Inputs

  • A list of merged pull request titles and numbers.
  • The target release version (e.g. 1.4.0).

Outputs

  • A Markdown changelog section with the version header and grouped bullet points, ready to paste into CHANGELOG.md.

Acceptance criteria

  • Every input PR appears exactly once in the output.
  • Entries are grouped under Features, Fixes and Docs headings.
  • The version header matches the provided version.

Examples

Input: PRs #12 Add export button (feature), #13 Fix crash on empty list (fix). Output:

## 1.4.0
### Features
- Add export button (#12)
### Fixes
- Fix crash on empty list (#13)

Limitations

  • Does not infer change type when a PR is untagged; it asks for clarification.
  • English output only in v0.1.

Test cases

  • TC-1: three PRs across all groups produce three grouped sections.
  • TC-2: an untagged PR triggers a clarification request rather than a guess.
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. 5d ago First seen · 57 lines · 26 tokens per session scan A 0cf118a87181

Subscribe to this mod's changes

changelog-writer is a skill published in the GitHub repository migmcc/agent-skill-quality-gate (2 stars, last pushed 2mo ago), licensed MIT. It adds 26 tokens to every session and 357 once invoked, about $0.0001 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.