release-notes

release-notes is a skill for Claude Code, Codex from jazzyalex/agent-sessions. It costs 56 tokens per session (2,432 once invoked), scanned A, original, MIT.

Guidance for writing user-facing release notes, such as a README update, GitHub release description, or in-app update message. Release notes summarize what users will notice, while a changelog records detailed development history.

In plain words
What is it for?
Curate release highlights, features, improvements, and fixes for Agent Sessions releases without changing the full internal changelog history.
Why use it?
It keeps public release communication concise and focused on user-visible changes. This prevents internal development details from overwhelming people installing the update.

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

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 release-notes

README.md
[![agentmods](https://agentmods.dev/badge/skills/jazzyalex/agent-sessions/release-notes.svg)](https://agentmods.dev/skills/jazzyalex/agent-sessions/release-notes)
Your own site
<a href="https://agentmods.dev/skills/jazzyalex/agent-sessions/release-notes"><img src="https://agentmods.dev/badge/skills/jazzyalex/agent-sessions/release-notes.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,432 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 $0.00056 $0.02432
Opus 5 $0.00028 $0.01216
Sonnet 5 $0.00011 $0.00486
Haiku 4.5 $0.00006 $0.00243

Measured 4d ago against content hash f30ebf417585, 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 4d 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/release-notes/SKILL.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release Notes (Agent Sessions)

CHANGELOG vs. release notes (read first)

These are two different documents with opposite jobs. Do not apply this skill to the first one.

CHANGELOG (docs/CHANGELOG.md) Release notes (README "What's New", GitHub release, Sparkle, website)
Audience Internal / maintainers (but the curated top feeds users) Users
Job Working development history + a curated release section The net change a user sees on update
Granularity Granular bullets while in [Unreleased]; curated headings at release Curated, collapsed, headline-first
This skill Governs its curated section (Highlights/Features/Bug Fixes); leaves the granular working bullets alone Governs all of it

The CHANGELOG is both the source history and the origin of the derived notes — because the deploy tool generates Sparkle/GitHub notes from it (see "How the derived notes are generated"). While developing, [Unreleased] may hold flat granular bullets; that's fine. At release, you curate that section into structured headings by applying the rule below. Don't delete real history — demote it to ### Improvements. Everything below is the curation rule.

Overview

Release notes describe the net change from the last shipped release to this one — the delta a user actually experiences when they update. They are not a replay of the CHANGELOG, and not a log of the work done during the cycle.

Core principle: ship the destination, not the journey. A user who updates from X to Y never saw any intermediate state. Everything that was built, refined, redesigned, and fixed between X and Y and never shipped to them is invisible — and must stay invisible in the notes.

This is the single rule most release notes get wrong, because the author lists what they worked on (commits, effort) instead of what changed for the user (the diff between two shipped versions).

The Iron Rule

A change earns a line only if it is observable as a difference between the previous shipped release and this one.

Read the full file on GitHub · 152 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. 4d ago First seen · 152 lines · 56 tokens per session scan A f30ebf417585

Subscribe to this mod's changes

release-notes is a skill published in the GitHub repository jazzyalex/agent-sessions (842 stars, last pushed today), licensed MIT. It adds 56 tokens to every session and 2,432 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

kirby-collections-and-navigation

Builds Kirby listings, pagination, search, filtering/sorting/grouping, and navigation menus. Use when implementing collection logic in templates/controllers/snippets.

bnomei/kirby-mcp · 37 tokens

kirby-routing-and-representations

Implements custom Kirby routes and content representations (.json/.xml/.rss), including redirects, sitemap endpoints, and URL pattern filtering. Use when building endpoints, redirects, or representation templates that change how URLs resolve.

bnomei/kirby-mcp · 50 tokens

kirby-scaffold-page-type

Scaffolds a new Kirby page type (blueprint + template, optional controller/model) using project roots, index tools, and Panel field/section references. Use when creating a new page type or extending an existing blueprint/template.

bnomei/kirby-mcp · 53 tokens

kirby-debugging-and-tracing

Diagnoses Kirby rendering/runtime issues using MCP runtime rendering, dump traces, and template/snippet/controller indexes. Use when outputs are wrong, errors occur, or tracing execution paths is required.

bnomei/kirby-mcp · 45 tokens

kirby-forms-and-frontend-actions

Implements frontend forms and actions in Kirby (contact forms, file uploads, email with attachments, creating pages from frontend). Use when handling user input or building submission flows.

bnomei/kirby-mcp · 43 tokens

kirby-headless-api

Exposes Kirby content to headless clients using the API, KQL, and JSON representations. Use when building API endpoints, KQL queries, or headless frontends.

bnomei/kirby-mcp · 41 tokens