changelog-writer

changelog-writer is a skill for Claude Code from mocraimer/mo-cc-plugins. It costs 125 tokens per session (1,454 once invoked), scanned A, original, MIT.

An automated tool that reviews changes in a Git repository, a project history system, and writes readable release-note entries in Keep a Changelog format, a common changelog layout.

In plain words
What is it for?
Use it during scheduled checks to track commits since the last checkpoint and maintain a growing changelog draft.
Why use it?
It explains actual code changes instead of relying only on commit messages, keeps entries from earlier runs, and avoids reporting the same changes repeatedly.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths.

Part of the loop-recipes plugin — 11 skills shipped together

Good fit Use it during scheduled checks to track commits since the last checkpoint and maintain a growing changelog draft.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mocraimer/mo-cc-plugins/changelog-writer
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.

Any agent
npx skills add mocraimer/mo-cc-plugins --skill changelog-writer
Clone the repo
git clone --depth 1 https://github.com/mocraimer/mo-cc-plugins

Made for: Claude Code.

Or install loop-recipes, the plugin that ships this one along with the rest of its 11 skills.

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/mocraimer/mo-cc-plugins/changelog-writer.svg)](https://agentmods.dev/skills/mocraimer/mo-cc-plugins/changelog-writer)
Your own site
<a href="https://agentmods.dev/skills/mocraimer/mo-cc-plugins/changelog-writer"><img src="https://agentmods.dev/badge/skills/mocraimer/mo-cc-plugins/changelog-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 125 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,454 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 $0.00125 $0.01454
Opus 5 $0.00063 $0.00727
Sonnet 5 $0.00025 $0.00291
Haiku 4.5 $0.00013 $0.00145

Measured 8d ago against content hash d947b3db6895, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 8d 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/loop-recipes/skills/changelog-writer/SKILL.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Changelog Writer

You are a changelog generation agent running as a recurring /loop iteration. Your job: read commits since the last checkpoint, analyze actual code diffs to understand what changed, and generate human-readable changelog entries in Keep-a-Changelog format. Entries accumulate across sessions — never overwrite previous work.

State Management

State file: ~/.claude/loop-recipes/changelog-writer-state.md Changelog draft: ~/.claude/loop-recipes/changelog-draft.md

On Start — Read State

  1. Read ~/.claude/loop-recipes/changelog-writer-state.md. If it does not exist, initialize:

    ---
    status: idle
    last_checkpoint_commit: ""
    last_checkpoint_time: "1970-01-01T00:00:00Z"
    total_entries: 0
    processed_commits: []
    ---
    # Changelog Writer Log
    
  2. If status: in-progress with a locked_by field set and locked_by timestamp is less than 10 minutes old, a previous iteration is still running. Output "Previous iteration still running — skipping." and stop. If locked_by is older than 10 minutes, treat as stale (previous iteration likely crashed), clear it, and proceed.

  3. Set locked_by: <current_timestamp> and status: in-progress.

  4. Ensure ~/.claude/loop-recipes/ directory exists (mkdir -p).

  5. Read last_checkpoint_commit and processed_commits for deduplication. If processed_commits exceeds 500 entries, trim the oldest entries to keep the most recent 500.

On End — Write State

After every iteration:

  • Clear locked_by, set status: idle
  • Update last_checkpoint_commit to the latest processed commit hash
  • Update last_checkpoint_time to current timestamp
  • Update total_entries count
  • Add newly processed commit hashes to processed_commits
  • Append iteration summary to log section

Iteration Logic

Step 1: Find New Commits

Determine what's new since the last checkpoint:

git log --since="<last_checkpoint_time>" --pretty=format:"%H" --no-merges 2>/dev/null

Read the full file on GitHub · 136 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. 8d ago First seen · 136 lines · 125 tokens per session scan A d947b3db6895

Subscribe to this mod's changes

changelog-writer is a skill published in the GitHub repository mocraimer/mo-cc-plugins (2 stars, last pushed 5mo ago), licensed MIT. It adds 125 tokens to every session and 1,454 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 2026-08-31.