image-generation-mcp: Skill for Claude Code

.claude/skills/writing-release-notes/SKILL.md

writing-release-notes is a skill for Claude Code from pvliesdonk/image-generation-mcp. It costs 117 tokens per session (5,108 once invoked), scanned A, a copy of writing-release-notes, MIT.

A skill for writing release-note pages stored under docs/releases. Release notes are human-readable explanations of what changed in a software release.

In plain words
What is it for?
Use it to research and draft release notes for release candidates or stable releases, including the correct version page and change summary.
Why use it?
It turns commits, pull requests, and linked issues into an evidence-based release story instead of a raw change list.

Skill for Claude Code

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

This is pvliesdonk/image-generation-mcp's own configuration. It tells Claude Code how to work on image-generation-mcp 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 image-generation-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to pvliesdonk/image-generation-mcp. 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/pvliesdonk/image-generation-mcp/main/.claude/skills/writing-release-notes/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/pvliesdonk/image-generation-mcp

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 writing-release-notes

README.md
[![agentmods](https://agentmods.dev/badge/skills/pvliesdonk/image-generation-mcp/writing-release-notes/github.svg)](https://agentmods.dev/skills/pvliesdonk/image-generation-mcp/writing-release-notes)
Your own site
<a href="https://agentmods.dev/skills/pvliesdonk/image-generation-mcp/writing-release-notes"><img src="https://agentmods.dev/badge/skills/pvliesdonk/image-generation-mcp/writing-release-notes/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 writing-release-notes

Your own site · 80×15
<a href="https://agentmods.dev/skills/pvliesdonk/image-generation-mcp/writing-release-notes"><img src="https://agentmods.dev/badge/skills/pvliesdonk/image-generation-mcp/writing-release-notes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 117 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,108 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 100% copy Near-identical to another mod 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 $0.00117 $0.05108
Opus 5 $0.00059 $0.02554
Sonnet 5 $0.00023 $0.01022
Haiku 4.5 $0.00012 $0.00511

Measured 9d ago against content hash 5b304e723b43, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

writing-release-notes 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.

Origin

This is a copy

100% identical to writing-release-notes — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/skills/writing-release-notes/SKILL.md · 404 lines

How it starts

The opening of the file, as written. The whole thing — 404 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Writing release notes

The pages under docs/releases/ are the canonical human-facing narrative of each release; the GitHub release body is a summary plus a link to them, and CHANGELOG.md is the machine-written commit-level audit trail. This skill is the contract for producing a page: what to research, what counts as evidence, what the page looks like, and which gates it must pass. Every requirement below was established empirically by trial runs recorded on pvliesdonk/fastmcp-server-template#347; where this skill says "must", a trial produced the failure the rule prevents.

Inputs

You are given, or must derive first:

  • TAG / VERSION — the stable release (e.g. v3.2.0 / 3.2.0). At prepare time (an open release PR, tag not yet created) these name the release being prepared; an rc target still drafts its stable minor's page.
  • MINOR — the series (e.g. 3.2); the page is docs/releases/MINOR.md.
  • PREV — the highest stable tag strictly below the target version (series-aware, sort -V); empty on a first release.
  • RANGE_END — where the research range ends, always a commit SHA. After a release this is the tagged commit; at prepare time it is the release PR's source commit, because the tag does not exist yet. The evidence rules below are identical either way — only the range endpoints move. A prepare-time draft is refreshed (branch force-pushed) alongside any re-dispatch of the release PR.
  • Mode — new page (the minor's page does not exist: write the whole page), patch append (the page exists but does not yet cover the target patch release, Z > 0: add one section inside the patch sentinels; leave the rest of the page alone unless it is factually wrong), or redraft (the page already covers the target — an X.Y.0 page drafted at prepare time, or any target whose RELEASE-SUMMARY marker an earlier candidate already wrote: update the covering section and its summary block in place, and never append a duplicate section for a release the page already covers).
  • Watermark — an existing page carries an invisible <!-- notes-range-end: SHA --> comment recording where its last accepted draft's research ended. This is the incremental-research anchor for the modes below.
  • Full-redraft flag — the operator may set it on either dispatch (Release Prepare threads it through to the notes job); it suspends the watermark's cache role for that one run (see the override below).

Read the full file on GitHub · 404 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. 9d ago First seen · 404 lines · 117 tokens per session scan A 5b304e723b43

Subscribe to this mod's changes

writing-release-notes is a skill published in the GitHub repository pvliesdonk/image-generation-mcp (1 stars, last pushed 2d ago), licensed MIT. It adds 117 tokens to every session and 5,108 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to writing-release-notes, differing in 0 lines, and is treated as a copy.