changelog

changelog is a skill for Claude Code, Codex from VGrss/Acumen. It costs 35 tokens per session (1,009 once invoked), scanned A, original, Apache-2.0.

A user-focused record of changes made to a product over a period of time, assembled from pull requests and commits. Unlike a commit log, it explains what users can do now.

In plain words
What is it for?
Use it after shipping, at the end of a sprint, or for a release to group changes by theme and write user-facing updates, with an optional video script.
Why use it?
It saves time translating technical development history into release notes that customers and other non-engineers can understand.

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/vgrss/acumen/changelog
Any agent
npx skills add VGrss/Acumen --skill changelog
Clone the repo
git clone --depth 1 https://github.com/VGrss/Acumen

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 changelog

README.md
[![agentmods](https://agentmods.dev/badge/skills/vgrss/acumen/changelog.svg)](https://agentmods.dev/skills/vgrss/acumen/changelog)
Your own site
<a href="https://agentmods.dev/skills/vgrss/acumen/changelog"><img src="https://agentmods.dev/badge/skills/vgrss/acumen/changelog.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,009 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 5.1 $0.00035 $0.01009
Opus 5 $0.00017 $0.00504
Sonnet 5 $0.00007 $0.00202
Haiku 4.5 $0.00003 $0.00101

Measured 5d ago against content hash f5db71b09d82, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

changelog 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 5d 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.

.agents/skills/changelog/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MANDATORY PREPARATION

Invoke /product-thinking — it contains the Context Gathering Protocol and the AI Slop Test. Follow the protocol before proceeding.


Mindset

A changelog is not a commit log. It's a story about what changed for users, written in their language. Engineers care about what was built. Users care about what they can do now. A good changelog bridges both — it's specific enough for engineers to recognize their work, and clear enough for users to understand the impact.

Step 1: Gather Parameters

Ask the user:

  1. Time range — what period does this changelog cover? Examples: "last 7 days", "last month", "since v2.1", "since 2026-03-01". If provided as the argument, use that.
  2. Format — text only, or text and video script? If video, the changelog will include a companion script suitable for a walkthrough recording.

Step 2: Analyze Changes

Pull PR and Commit History

Use git log to gather all commits and merged PRs in the specified time range. For each:

  • Read the PR title, description, and linked issues
  • Identify what changed from the user's perspective (not the implementation perspective)
  • Group changes by theme, not by PR

Ground in Feature Context

Read .acumen/features.md to understand the business context behind each change:

  • Which feature area does this change belong to?
  • Is this a new capability, an enhancement, or a fix?
  • Which persona benefits?

Read .acumen.md for product positioning — frame changes in terms of the product's value proposition, not its architecture.

Categorize

Group changes into:

  • New — capabilities that didn't exist before
  • Improved — existing capabilities that got better
  • Fixed — things that were broken and are now working
  • Changed — behavior changes that existing users should know about (potential breaking changes)

Drop changes that are purely internal (refactors, dependency updates, CI changes) unless they affect performance or reliability in a way users would notice.

Read the full file on GitHub · 119 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. 5d ago First seen · 119 lines · 35 tokens per session scan A f5db71b09d82

Subscribe to this mod's changes

changelog is a skill published in the GitHub repository VGrss/Acumen (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 35 tokens to every session and 1,009 once invoked, about $0.0002 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.