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 systemfsoftware/comment-checker --skill changesetsgit clone --depth 1 https://github.com/systemfsoftware/comment-checkerWrote 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/systemfsoftware/comment-checker/changesets)<a href="https://agentmods.dev/skills/systemfsoftware/comment-checker/changesets"><img src="https://agentmods.dev/badge/skills/systemfsoftware/comment-checker/changesets/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/systemfsoftware/comment-checker/changesets"><img src="https://agentmods.dev/badge/skills/systemfsoftware/comment-checker/changesets.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 | $0.00042 | $0.00723 |
| Opus 5.5 | $0.00017 | $0.00289 |
| Sonnet 5.5 | $0.00008 | $0.00145 |
| Haiku 4.5 | $0.00004 | $0.00072 |
Grade A, and why
changesets 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 10d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Treat a changeset as the release note for the complete PR, not as a log of work performed along the way. Finalize it after the current implementation scope and focused validation are complete.
Workflow
- Inspect the complete diff from the merge base, including changeset files already introduced by the PR, and identify directly affected published packages.
- Classify impact across source types, runtime behavior, entrypoints, required services, lifecycle, and persisted or wire data.
- Perform the breaking audit below.
- Record a reason no changeset is required, or update the PR's existing changeset. Create one only when the PR does not have one. When required, read authoring.md.
- Validate package names, frontmatter, bump policy, and a concise consumer-facing description.
Do not include unrelated worktree changes.
PR-level consolidation
The default is one changeset file per PR. One file can name several packages and summarize several related fixes or additions. Successive prompts, commits, and subtasks within the same PR update that file. If implementation resumes after a changeset was drafted, revise it during the next finalization pass.
Use separate files only when a maintainer requests the split or the PR contains independent changes that need separate release notes.
Requirement
Create a changeset for observable runtime behavior changes, including bug fixes; exported value or public type changes; entrypoint or export-map changes; changes to required services, errors, ownership, defaults, or lifecycle; and persisted, serialization, protocol, or wire-format changes.
Tests-only changes, behavior-preserving internal refactors, documentation or JSDoc maintenance, and unpublished tooling normally do not need one. When unclear, inspect exports and consumer-visible declarations rather than inferring from source location.
Breaking Audit
A change is breaking when valid existing consumer code, configuration, or data must change to keep compiling or behaving according to the previous contract. Audit every surface:
What ships with it
1 file 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.
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.
- 10d ago First seen · 76 lines · 42 tokens per session scan A c28b2a72be12
changesets is a skill published in the GitHub repository systemfsoftware/comment-checker (4 stars, last pushed 3d ago), licensed Apache-2.0. It adds 42 tokens to every session and 723 once invoked, about $0.0002 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 2026-10-19.
Other skills, from other repositories
release
Automated release management - version updates, changelog generation, git tagging, and GitHub release creation.
slack-changelog
Turns what changed in a release into a Slack changelog a non-technical audience can read: filtered to what they would actually notice, one bullet per idea, plain language, no code vocabulary. Works out the scope itself across however many repositories sit in the working directory (a project can span several…
changelog
Use when the user wants a changelog, release notes, or asks what changed since the last release.
version-bump
Automated semantic versioning and release workflow for Claude Code plugins. Handles version increments across package.json, marketplace.json, plugin.json manifests, build verification, git tagging, GitHub releases, and changelog generation. npm publishing is done by the tag-triggered GitHub Actions workflow through…
batch
Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.
github
GitHub via gh CLI: PRs, issues, reviews, repos, auth.