changelog

changelog is a skill for Claude Code, Codex from rbah31/claude-code-workflow. It costs 87 tokens per session (625 once invoked), scanned A, original, Apache-2.0.

A workflow for turning completed sprint records into user-facing changelogs, release notes, and feature announcements. A sprint is a planned period of product work.

In plain words
What is it for?
Use it after a sprint to create a full changelog, release notes, and shorter announcements based on the work that shipped.
Why use it?
It helps translate technical work into updates that users can understand, while leaving internal-only changes out of the announcement.

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/rbah31/claude-code-workflow/changelog
Any agent
npx skills add rbah31/claude-code-workflow --skill changelog
Clone the repo
git clone --depth 1 https://github.com/rbah31/claude-code-workflow

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/rbah31/claude-code-workflow/changelog.svg)](https://agentmods.dev/skills/rbah31/claude-code-workflow/changelog)
Your own site
<a href="https://agentmods.dev/skills/rbah31/claude-code-workflow/changelog"><img src="https://agentmods.dev/badge/skills/rbah31/claude-code-workflow/changelog.svg" alt="Measured on agentmods" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 625 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 $0.00087 $0.00625
Opus 5 $0.00044 $0.00313
Sonnet 5 $0.00017 $0.00125
Haiku 4.5 $0.00009 $0.00063

Measured 5d ago against content hash d33d61ada7b1, 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.

.claude/skills/changelog/SKILL.md · 82 lines

What it actually says

Changelog & Release Notes

You generate user-facing communication about what changed in the product. You read sprint artifacts and translate technical changes into benefits users understand.

Step 1 — Understand what shipped

Read the latest sprint artifacts:

  1. tasks/sprints/sprint-XX/plan.md — what was planned
  2. tasks/sprints/sprint-XX/build-output.md — what was built
  3. tasks/sprints/sprint-XX/retrospective.md — summary
  4. briefs/marketing-context.md — current positioning and tone

Classify each change:

  • User-facing feature → goes in the changelog
  • User-facing fix → goes in the changelog (bug fixes section)
  • Internal/technical → skip (users don't care about refactors)
  • Security fix → mention without details ("security improvements")

Step 2 — Write the changelog

Produce three versions in content/changelog/sprint-XX/:

changelog.md — Full changelog (for the website/docs)

# [Product] — [Version or Date]

## New
- **[Feature name]** — [1-2 sentences: what it does, why it matters]

## Improved  
- **[Improvement]** — [what changed, what's better now]

## Fixed
- **[Bug]** — [what was broken, now works correctly]

social-post.md — Short social media version

[Emoji] [Product] update:

[1-2 key highlights, punchy, benefit-focused]

[Optional: screenshot or demo link]

discord-announcement.md — Community announcement

[Adapted to the community's tone — more casual, more detailed, 
invites feedback]

Step 3 — Tone calibration

Match the product's voice from marketing-context.md:

  • Technical audience → be specific, mention the how
  • Non-technical audience → focus on the what and why
  • Community-driven → invite feedback, celebrate contributors
  • Enterprise → focus on reliability, security, compliance

Rules

  • Never exaggerate. If it's a small fix, say so
  • Never mention security vulnerabilities in detail
  • Always frame changes as benefits ("You can now..." not "We added...")
  • Include a call to action when relevant ("Try it now", "Let us know")
  • If nothing user-facing shipped, don't force a changelog — skip it
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 · 82 lines · 87 tokens per session scan A d33d61ada7b1

Subscribe to this mod's changes

changelog is a skill published in the GitHub repository rbah31/claude-code-workflow (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 87 tokens to every session and 625 once invoked, about $0.0004 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 2026-08-31.