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 epam/ai-dial-ui-kit --skill release-notesgit clone --depth 1 https://github.com/epam/ai-dial-ui-kitWrote 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/epam/ai-dial-ui-kit/release-notes)<a href="https://agentmods.dev/skills/epam/ai-dial-ui-kit/release-notes"><img src="https://agentmods.dev/badge/skills/epam/ai-dial-ui-kit/release-notes/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/epam/ai-dial-ui-kit/release-notes"><img src="https://agentmods.dev/badge/skills/epam/ai-dial-ui-kit/release-notes.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 | $0.00110 | $0.03268 |
| Opus 5.5 | $0.00044 | $0.01307 |
| Sonnet 5 | $0.00022 | $0.00654 |
| Haiku 4.5 | $0.00011 | $0.00327 |
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 6d 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 — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@epam/ai-dial-ui-kit — release-notes enhancer
The CI publishes a release for every tag with bullets that are the raw PR titles. Those bullets carry noise — conventional-commit prefixes (feat(scope):, fix(area):), cross-project issue refs from consumer repos (ai-dial-chat, ai-dial-admin-frontend), repeated scope prefixes, tooling/internal items under ## Other, and a ## Tests section that has zero consumer impact. The stable releases at https://github.com/epam/ai-dial-ui-kit/releases are what those raw notes look like after a human editorial pass. This skill reproduces that pass.
You are running in a forked, isolated context. Read and research freely — only the final summary you return reaches the main conversation. All file writes happen in this fork; the draft lands at .claude/release-notes/<tag>-draft.md.
When to use
- "Enhance the release notes for
0.11.0" - "Look at the latest release notes and refine them"
- "The CI just published
<tag>, make it readable" - "Polish the release notes for the current tag"
Do not trigger on requests like "what changed in 0.10.0?" — that is a recall question, not a notes-editing task.
Inputs
tag = $tag — the GitHub release tag to enhance (e.g. 0.11.0, 0.10.0). If empty, pick the most recent tag from gh release list --limit 5 and confirm with the user before editing.
Workflow
1. Resolve target and reference styles
gh release view <tag> --json body,name,tagName— capture the raw CI notes.gh release list --limit 10— locate the previous stable tag.gh release view <prev-tag> --json body— style anchor. Match their terseness; one line per bullet.git log <prev-tag>..<tag> --oneline— full commit list for the range, to spot commits the CI dropped.
2. Pull source context for each bullet
For every bullet in the raw notes:
- Parse out the trailing
(Issue #<issue>) (#<PR>)or just(#<PR>). Canonical reference order is#<issue> (#<PR>). gh pr view <PR> --json title,body,labels— read the PR body for the why and what-it-replaces; the title is too compressed.- For bullets without a PR number, find the commit with
git log <prev-tag>..<tag> --oneline | grep -i <keywords>andgit show <hash>— fold into a related entry rather than leaving standalone.
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.
- 6d ago First seen · 232 lines · 110 tokens per session scan A 658de513a950
release-notes is a skill published in the GitHub repository epam/ai-dial-ui-kit (10 stars, last pushed today), licensed Apache-2.0. It adds 110 tokens to every session and 3,268 once invoked, about $0.0004 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 2026-09-19.
Other skills, from other repositories
pre-release-check
The final gate before a release is cut — go green, reconcile the release PR against what actually landed, sweep what CI can't see, check the roadmap and ADR statuses, optionally deep-review, then return a ship-or-hold verdict.
github
GitHub via gh CLI: PRs, issues, reviews, repos, auth.
git-safety
Git safety rules. INVOKE WHEN: git push, force push, git reset, git clean, destructive git, push force, reset hard. NEVER force push or do destructive git operations.
release-safety
Release safety rules. INVOKE WHEN: yarn release, npm publish, release canary, release packages, publishing, skip checks, skip tests. NEVER skip checks or tests without explicit permission.
changelog
Turn a range of commits or merged PRs into a changelog entry grouped by change type. Use when the user asks for release notes, a changelog, or "what changed" between two points.
goal-release
Cut a release end to end: use the draft-release skill to open the release PR and draft GitHub release, wait for CI to turn green, run the merge-pr skill to merge the release PR, then update the Homebrew formula from the published release assets. Use when the user wants to draft and merge a release in one go, or…