What is release-notes?

A release-note writer that turns a range of Git commits into user-facing changelog text. It groups changes into features, fixes, and breaking changes, which are changes that may require users to adjust their code or workflow.

Use it to prepare release notes or changelog entries for a version, milestone, or selected range of Git history.

It removes the need to manually interpret internal commit messages and rewrite them for users.

release-notes — Skill for Claude Code and Codex by jnMetaCode: A release-note writer that turns a range of Git…

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/jnmetacode/ai-coding-guide/templates

Any agent

npx skills add jnMetaCode/ai-coding-guide --skill templates

Clone the repo

git clone --depth 1 https://github.com/jnMetaCode/ai-coding-guide

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jnmetacode/ai-coding-guide/templates.svg)](https://agentmods.dev/skills/jnmetacode/ai-coding-guide/templates)

Your own site

<a href="https://agentmods.dev/skills/jnmetacode/ai-coding-guide/templates"><img src="https://agentmods.dev/badge/skills/jnmetacode/ai-coding-guide/templates.svg" alt="Measured on agentmods" height="20"></a>

Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 610 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.

Model	Per session	Once invoked
Fable 5	$0.00059	$0.00610
Opus 5	$0.00030	$0.00305
Sonnet 5	$0.00012	$0.00122
Haiku 4.5	$0.00006	$0.00061

Measured 3d ago against content hash 6c21c88af17f, 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 3d 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.

codex/templates/SKILL.md · 60 lines

What it actually says

Release Notes Drafter

Generate clear, user-facing release notes from git log between two refs.

When to fire

User mentions: "release notes", "changelog", "what shipped", "summarize this milestone"
A git ref range or version tag is in scope (e.g. v1.2.0..HEAD, last-tag..main)

Inputs you should gather

The two refs (default: <latest tag>..HEAD if user didn't specify)
Audience: end users (default), API consumers, internal team
Output format: markdown (default), JSON, or plain text

Steps

Run git log <from>..<to> --pretty=format:'%h%x09%s%x09%an' --no-merges
For each commit, classify:
- feat: / add: → Features
- fix: / bugfix: → Fixes
- BREAKING CHANGE: (in body) → Breaking (top of doc, explicit migration note)
- everything else (chore:, docs:, refactor:, test:) → omit unless user-visible
For each entry, rewrite the commit message in user-facing language (no feat(api): prefix; no internal jargon)
If there's a PR number in the commit ((#1234)), link it
Group by category, sort by impact (breaking > features > fixes > minor)

Output template

## <version> — <date>

### ⚠️ Breaking changes
- <one-sentence summary>. **Migration:** <what to do>. ([#PR])

### ✨ Features
- <user-visible benefit>. ([#PR])

### 🐛 Fixes
- <symptom that's now fixed>. ([#PR])

Gotchas

Don't dump raw commit messages — rewrite from the user's perspective
Squash-merged repos: each merge commit covers many internal commits; read the PR description for context
Conventional Commit chore: and docs: rarely belong in user-facing notes
If BREAKING CHANGE: is in the body of a feat:, the entry must surface as Breaking, not Feature
For monorepos, prefix entries with the affected package name ([@org/auth])

References

See references/conventional-commits.md for the full type list
See examples/v1.2.0.md for a polished sample

Files

What ships with it

3 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.

3d ago First seen · 60 lines · 59 tokens per session scan A 6c21c88af17f

Subscribe to this mod's changes

release-notes is a skill published in the GitHub repository jnMetaCode/ai-coding-guide (512 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 59 tokens to every session and 610 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.

Git and workflow Releases Writing and docs ai-coding ai-programming ai-tools aider best-practices chinese

snip

You are an expert at writing declarative YAML filters for snip, a CLI proxy that reduces LLM token consumption by filtering shell output.

edouard-claude/snip · 0 tokens

v1-milestone

Factory line for executing one milestone of the HAR v1.0.0 refactor (epic os-factory/har#225) — plan the wave of parallel subagents, implement each issue in its own HAR slot, ship stacked PRs, run the fixture-e2e milestone gate, and hand off for review. Use when asked to "run the next v1 milestone", "work on v1.0.0"…

os-factory/har · 110 tokens

cost-mode

Cost-conscious Claude Code mode. Reduces output tokens 40-70% and overall costs 30-60% by enforcing concise responses, smart model routing, and efficient workflow patterns. Keeps full technical accuracy. Activate with /cost-mode or "enable cost mode". Auto-triggers on mentions of budget, cost, tokens, or spending.

Sagargupta16/claude-cost-optimizer · 71 tokens

standup

Read-only release + backlog recap. Reports the last release, commits-since-tag classified by conventional-commit type with the semver bump they trigger and pushed-vs-origin state, the backlog bucketed (open/picked-up/dropped with epic parent→child nesting), the roadmap epics with their per-task tallies, and condensed…

friedbotstudio/baseline · 138 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

coograph-archive

Archive a completed change. Use when implementation is done and the change is ready to be moved to the archive.

paullukic/coograph · 27 tokens