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 agentmods add skills/validmind/atryum/release-notesnpx skills add validmind/atryum --skill release-notesgit clone --depth 1 https://github.com/validmind/atryumWhat 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 | $0.00070 | $0.00732 |
| Opus 5 | $0.00035 | $0.00366 |
| Sonnet 5 | $0.00014 | $0.00146 |
| Haiku 4.5 | $0.00007 | $0.00073 |
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 2d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release notes
Why this exists
just release <tag> prepends the CHANGELOG.md section matching the tag to
GitHub's auto-generated release notes (--generate-notes supplies the PR
list, contributor credits, and compare link; the changelog section supplies
the human-readable story). If no matching section exists, the release still
goes out with generated notes only — so the changelog is the part that takes
judgment, and it's this skill's job.
What good notes look like
The audience is someone operating or upgrading atryum, not someone who watched the commits land. They want to know what changed in behavior, what they must do before or after upgrading, and whether anything is security-relevant. Branch names, internal refactor jargon, and commit shorthand don't communicate that — describe the effect, not the diff.
Follow Keep a Changelog 1.0.0:
group entries under Added / Changed / Deprecated / Removed /
Fixed / Security, omitting empty groups. The Security section
deserves particular care in this project — auth gating, judge hardening,
trust boundaries, and anything an operator would want to prioritize an
upgrade for belongs there, even if the commit called it a "fix" or "feat".
How to build the section
- Find the previous release tag (
git tag --sort=-creatordate, ignore backup/scratch tags) and review everything since:git log <prev>..HEAD. PR titles alone hide detail — a single PR here can carry a dozen meaningful commits, so read the commit subjects (and bodies where the subject is vague) before summarizing. - Decide or confirm the version. Semver from the reader's perspective: behavior-visible features → minor, only fixes → patch, breaking config/API/CLI changes → call them out explicitly and bump accordingly.
- Update
CHANGELOG.md:- New heading
## [x.y.z] - YYYY-MM-DD(today's date, novprefix — release-push strips thevfrom the tag when matching). - Fold in anything sitting under
[Unreleased], leaving that section present but empty. - Keep the compare links at the bottom of the file in sync.
- New heading
- Sanity-check the release path:
just release <tag>builds from a pristine local clone of the tag (at../atryum-release-<tag>) and reads the notes from the tag's ownCHANGELOG.md— so the order is commit the changelog, tag, push the tag, then release. Anything not committed and tagged simply isn't in the release, notes included.
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.
- 2d ago First seen · 57 lines · 70 tokens per session scan A 8a1cf646bd9a
release-notes is a skill published in the GitHub repository validmind/atryum (11 stars, last pushed 21d ago), licensed Apache-2.0. It adds 70 tokens to every session and 732 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…