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.
npx skills add wyattowalsh/agents --skill changelog-writergit clone --depth 1 https://github.com/wyattowalsh/agentsWrote 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.
[](https://agentmods.dev/skills/wyattowalsh/agents/changelog-writer)<a href="https://agentmods.dev/skills/wyattowalsh/agents/changelog-writer"><img src="https://agentmods.dev/badge/skills/wyattowalsh/agents/changelog-writer/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.
<a href="https://agentmods.dev/skills/wyattowalsh/agents/changelog-writer"><img src="https://agentmods.dev/badge/skills/wyattowalsh/agents/changelog-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00046 | $0.01788 |
| Opus 5 | $0.00023 | $0.00894 |
| Sonnet 5 | $0.00009 | $0.00358 |
| Haiku 4.5 | $0.00005 | $0.00179 |
Grade A, and why
changelog-writer 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Changelog Writer
Generate changelogs, release notes, breaking change summaries, migration guides, and version bump recommendations from git history.
Scope: Changelog and release documentation only. NOT for git operations (git-workflow), documentation sites (docs-steward), or code review (review).
Dispatch
| $ARGUMENTS | Mode |
|---|---|
Empty / generate |
Generate changelog from recent commits |
release <version> |
User-facing release notes for specific version |
breaking |
Breaking change detection and summary |
migration <from> <to> |
Migration guide between two versions |
bump |
Semantic version recommendation based on changes |
| Unrecognized input | Ask for clarification, show mode menu |
Canonical Vocabulary
| Term | Definition |
|---|---|
| conventional commit | Commit following type(scope): description format |
| change type | Classification: feat, fix, refactor, perf, docs, chore, test, ci, build, style |
| breaking change | Backward-incompatible change, marked by ! or BREAKING CHANGE: footer |
| scope | Component affected, in parentheses after type |
| changelog entry | Formatted line item in a changelog section |
| release notes | User-facing summary of changes for a version |
| migration guide | Step-by-step instructions to upgrade between versions |
| semver bump | major (breaking), minor (feat), patch (fix) recommendation |
| unreleased | Changes since the last tagged version |
Mode 1: Generate Changelog
Default mode. Produces a Keep a Changelog formatted document.
Step 1: Classify Commits
Run the commit classifier script:
uv run python skills/changelog-writer/scripts/commit-classifier.py [--since <tag-or-date>] [--until <ref>] [--path <dir>]
Parse the JSON output. The script classifies each commit by conventional type and detects breaking changes.
Step 2: Format Changelog
Run the changelog formatter script:
uv run python skills/changelog-writer/scripts/changelog-formatter.py --input <classified-json> [--format keepachangelog|github|simple]
What ships with it
20 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.
- data/breaking-change-patterns.json 2.0 KB
- data/changelog-formats.json 1.4 KB
- evals/evals.json 2.0 KB
- evals/generate-changelog.json 582 B
- evals/implicit-trigger.json 468 B
- evals/negative-control.json 414 B
- evals/release-notes.json 604 B
- evals/version-bump.json 521 B
- references/changelog-conventions.md 4.9 KB
- references/commit-parsing.md 4.2 KB
- scripts/asset_toolkit/__init__.py 303 B runs code
- scripts/asset_toolkit/_shared.py 5.6 KB runs code
- scripts/asset_toolkit/common.py 3.0 KB runs code
- scripts/asset_toolkit/package.py 43 KB runs code
- scripts/asset_toolkit/validate_evals.py 11 KB runs code
- scripts/asset_toolkit/validate_hooks.py 13 KB runs code
- scripts/asset_toolkit/validate_skill.py 3.6 KB runs code
- scripts/changelog-formatter.py 5.0 KB runs code
- scripts/check.py 2.2 KB runs code
- scripts/commit-classifier.py 5.9 KB runs code
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.
- 11d ago First seen · 218 lines · 46 tokens per session scan A 967104cb74f0
changelog-writer is a skill published in the GitHub repository wyattowalsh/agents (5 stars, last pushed 9d ago), licensed MIT. It adds 46 tokens to every session and 1,788 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 2026-08-31.
Other skills, from other repositories
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.
updater_guide
Guidance for checking for and installing Row-Bot updates.