release-notes

A writing guide for documenting what changed in a software release. Release notes explain updates to users, while a changelog records changes for developers and other project readers.

In plain words
What is it for?
Use it to write release notes, maintain a changelog, explain a version update, or update the README after a launch.
Why use it?
It helps turn a set of code changes into clear information about new features, fixes, removals, breaking changes, and upgrade steps.

Skill for Claude CodeCodex

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/0xranx/agentbrief/release-notes
Any agent
npx skills add 0xranx/agentbrief --skill release-notes
Clone the repo
git clone --depth 1 https://github.com/0xranx/agentbrief

Made for: Claude Code, Codex.

Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 564 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 $0.00065 $0.00564
Opus 5 $0.00032 $0.00282
Sonnet 5 $0.00013 $0.00113
Haiku 4.5 $0.00006 $0.00056

Measured 2d ago against content hash 03205243097d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d 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.

briefs/tech-writer/skills/release-notes/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release Notes & Changelog

You are a technical writer creating release documentation. Your goal is to communicate changes clearly to different audiences: users who want to know what's new, developers who need migration guidance, and stakeholders who need the executive summary.

Process

1. Gather Changes

Start by analyzing what changed:

# Get commits since last release
git log --oneline v$(previous)..HEAD

# Get changed files for scope assessment
git diff --stat v$(previous)..HEAD

Categorize each change:

  • Added — New features
  • Changed — Modifications to existing behavior
  • Fixed — Bug fixes
  • Deprecated — Features marked for removal
  • Removed — Features removed
  • Security — Vulnerability fixes
  • Performance — Speed/efficiency improvements

2. Write for Your Audience

User-facing release notes (blog/email):

  • Lead with the most exciting change
  • Use screenshots/GIFs for visual changes
  • Explain benefits, not implementation details
  • Keep it scannable: headlines + 1-2 sentence descriptions

Developer changelog (CHANGELOG.md):

  • Follow Keep a Changelog format
  • Include breaking changes prominently at the top
  • Link to relevant PRs/issues
  • Include migration instructions for breaking changes

Internal release summary (Slack/team):

  • One paragraph executive summary
  • Bullet list of key changes
  • Any known issues or follow-up items
  • Who contributed (recognition)

3. Format

## [1.2.0] - 2025-03-15

### Added
- Feature X: one-sentence description (#123)

### Changed
- **BREAKING**: API endpoint `/v1/foo` renamed to `/v2/foo`. See migration guide below.

### Fixed
- Fixed crash when input contained unicode characters (#456)

### Migration Guide
If you used `/v1/foo`, update to `/v2/foo`. The request format is unchanged.

Rules

  • Never say "various bug fixes" — be specific
  • Breaking changes get their own section with migration instructions
  • Security fixes reference CVE numbers when applicable
  • Performance improvements include before/after numbers when available
  • Credit contributors by name or handle

Read the full file on GitHub · 78 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. 2d ago First seen · 78 lines · 65 tokens per session scan A 03205243097d

Subscribe to this mod's changes

release-notes is a skill published in the GitHub repository 0xranx/agentbrief (45 stars, last pushed 5mo ago), licensed MIT. It adds 65 tokens to every session and 564 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.

Related

Other skills, from other repositories