A generator that creates structured “what’s new” entries from a set of changes. The entries can then be routed to a project's chosen destination, such as release notes.

Use it to prepare Added, Changed, Deprecated, Removed, Fixed, or Security entries for a release or project update.

It separates writing change summaries from publishing them and avoids editing the final changelog directly.

How friedbotstudio/baseline configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to friedbotstudio/baseline. 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/friedbotstudio/baseline/main/.claude/skills/whatsnew/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/friedbotstudio/baseline

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/friedbotstudio/baseline/whatsnew/github.svg)](https://agentmods.dev/skills/friedbotstudio/baseline/whatsnew)

Your own site

<a href="https://agentmods.dev/skills/friedbotstudio/baseline/whatsnew"><img src="https://agentmods.dev/badge/skills/friedbotstudio/baseline/whatsnew/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/friedbotstudio/baseline/whatsnew"><img src="https://agentmods.dev/badge/skills/friedbotstudio/baseline/whatsnew.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 126 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 793 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.

Model	Per session	Once invoked
Fable 5.1	$0.00126	$0.00793
Opus 5.5	$0.00050	$0.00317
Sonnet 5.5	$0.00025	$0.00159
Haiku 4.5	$0.00013	$0.00079

Measured 1mo ago against content hash 103c67707d80, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

whatsnew 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 1mo ago.

The scan reads SKILL.md. This mod also ships 4 executable files (classifier.mjs, fragment-writer.mjs, route-resolver.mjs, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/whatsnew/SKILL.md · 33 lines

How it starts

The opening of the file, as written. The whole thing — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.

whatsnew — on-demand generator

Emits a structured "what's new" fragment for a set of changes. The fragment is a gitignored handoff buffer; a per-project routing workflow turns it into whatever surface the project wants. The generator makes no assumption about the destination, and it never touches CHANGELOG.md — semantic-release owns that file at release time.

This skill is not a mandatory workflow phase. It is invoked on demand (and, when a project wires whatsnew.route_workflow, handed off to that routing workflow). Version is never stored in the fragment: the routing target reads the shipped version at publish time.

Steps

Build the entries (main context). Decide the keepachangelog entries for the change — one object per user-visible change, not per file. Write a JSON array to an entries file (for example under .claude/state/whatsnew/), each object shaped { "category": "<Added|Changed|Deprecated|Removed|Fixed|Security>", "title": "<short headline>", "body": "<one or two sentences>", "highlight": <bool, optional> }.
Run the generator. Invoke the entrypoint with --slug <slug> --entries-file <path> (optionally --project-root <root>). It validates the entries, writes the fragment to .claude/state/whatsnew/<slug>.json, and resolves the optional routing target.
Routing (optional). If project.json → whatsnew.route_workflow names a workflow, that workflow is the documented consumer of the fragment; it reads the fragment and writes its own committed output. If the knob is absent or null, the generator still succeeds and the fragment simply sits at the conventional path unconsumed.

Companion files

whatsnew.mjs — the generator entrypoint. Reads the entries file, writes the fragment, reports the routing target.
fragment-writer.mjs — validates entries and serializes the fragment { slug, generated_at, entries[{category, title, body, highlight?}] }. No version field.
route-resolver.mjs — resolves project.json → whatsnew.route_workflow (string track id, or null by read-time default).
classifier.mjs — defines the canonical keepachangelog category set that fragment-writer.mjs validates entries against.

Read the full file on GitHub · 33 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

1mo ago First seen · 33 lines · 126 tokens per session scan A 103c67707d80

Subscribe to this mod's changes

whatsnew is a skill published in the GitHub repository friedbotstudio/baseline (14 stars, last pushed 13d ago), licensed Apache-2.0. It adds 126 tokens to every session and 793 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-09-03.

AI Safety Git and workflow Releases Writing and docs ai ai-coding ai-governance ai-security ai-tools

release-notes

Draft user-facing release notes from a git log range. Trigger when the user asks for "release notes", "changelog entry", or "what shipped this week" with a git ref range. Output is markdown sections grouped by Features / Fixes / Breaking with PR links.

jnMetaCode/ai-coding-guide · 59 tokens

ca-pr

Open a PR or finish branch disposition; route CI watching and post-merge cleanup to their owners. Merge and discard need explicit authority.

arbiterForge/codeArbiter · 30 tokens

release-and-changelog

Use when cutting a release, bumping a version, or writing release notes. Activate for keywords like "release", "version bump", "changelog", "release notes", "tag", "publish", "ship a release", "v1.x", "v2.x". Enforces version hygiene: SemVer respect, changelog discipline, atomic commits, tagged release. Always reflect…

duthaho/claudekit · 99 tokens

release

Prepare a declared release target, or preview it with --dry-run. Derive its version and require authorization before publication.

arbiterForge/codeArbiter · 26 tokens

ca-release