summarize-releases

A release-summary workflow that turns local version tags, changelogs, package versions, and commit history into a monthly “What’s New” documentation page and short announcement text. It reads the local Git copy rather than contacting GitHub or npm.

In plain words
What is it for?
Use it for monthly release roundups, changelog digests, scheduled release pull requests, Slack updates, and announcements.
Why use it?
It removes the need to manually collect changes from multiple release records and explain them in plain language. It also combines repeated entries from package changelogs.

Skill for Claude CodeCodex

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/nvidia/elements/summarize-releases
Any agent
npx skills add NVIDIA/elements --skill summarize-releases
Clone the repo
git clone --depth 1 https://github.com/NVIDIA/elements

Made for: Claude Code, Codex.

Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,672 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.

ModelPer sessionOnce invoked
Fable 5 $0.00074 $0.01672
Opus 5 $0.00037 $0.00836
Sonnet 5 $0.00015 $0.00334
Haiku 4.5 $0.00007 $0.00167

Measured 2d ago against content hash 7db9e7782cfb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

summarize-releases 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/collect-releases.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.agents/skills/summarize-releases/SKILL.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Summarize Releases

Turn recent NVIDIA Elements releases into a dated docs page that explains what changed and why users should care. Leave the repository with a focused, validated change that a scheduled agent can propose as a pull request.

Collect the evidence

Run the collector from the repository root. Pass the requested calendar month; otherwise the collector uses the previous calendar month.

mise exec -- node .agents/skills/summarize-releases/scripts/collect-releases.js

The script is the source of truth for:

  • the docs page path, URL, title, covered month, publication dates, layout, and collection tags
  • release tags and their creation dates
  • package names and versions from each tag
  • tagged package.json version checks
  • the matching section from each tagged CHANGELOG.md
  • repeated-commit merging across package changelogs
  • conventional commit metadata, messages, and changed-file statistics

The collector only reads the local Git clone. It does not call the GitHub API, query npm, or require a token.

Useful options:

mise exec -- node .agents/skills/summarize-releases/scripts/collect-releases.js --month 2026-07
mise exec -- node .agents/skills/summarize-releases/scripts/collect-releases.js --month 2026-07 --json

Use --include-prereleases only when the user wants preview releases.

For scheduled monthly runs, omit --month to collect the previous calendar month. Pass --month YYYY-MM for historical or explicit reruns. The collector treats the current month as month-to-date and rejects future months.

Check repository freshness

The collector can only report tags available in the clone. When the user requests the latest releases and the clone might be stale or shallow, fetch the public tags before collecting:

git fetch --tags origin

If fetching is unavailable, state that the result covers only the local tags. Do not claim that the report includes the latest releases.

Investigate the changes

Read the complete evidence packet before drafting. Treat changelog text as a lead, not a complete plain-language explanation.

Read the full file on GitHub · 153 lines

Files

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.

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.

  1. 2d ago First seen · 153 lines · 74 tokens per session scan A 7db9e7782cfb

Subscribe to this mod's changes

summarize-releases is a skill published in the GitHub repository NVIDIA/elements (83 stars, last pushed 2d ago), licensed Apache-2.0. It adds 74 tokens to every session and 1,672 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

nuxt-ui

Build UIs with @nuxt/ui v4 — 125+ accessible Vue components with Tailwind CSS theming. Use when creating interfaces, customizing themes to match a brand, building forms, or composing layouts like dashboards, docs sites, and chat interfaces.

nuxt/ui · 56 tokens

ui-development

Build UI pages and extensions for Falcon Foundry apps using React or Vue with the Shoelace design system and Foundry-JS. TRIGGER when user asks to "create a UI page", "build a UI extension", "add a Shoelace component", "call an API from the UI", runs foundry ui pages create or foundry ui run, or needs help with Vite…

CrowdStrike/foundry-skills · 113 tokens

vue-application-structure

Establishes or reviews the directory layout, component conventions, composable design, Pinia store structure, and Vue Router configuration for a Vue 3 TypeScript application. Invoked when the user asks to structure a Vue app, set up the project layout, or review Vue architecture.

soulcodex/agentic · 63 tokens

vue-component-testing

Applies the three-tier test taxonomy for Vue 3 applications: writes unit tests for composables and Pinia stores with Vitest, component tests for behaviour and user interactions with @testing-library/vue, and acceptance tests for full user flows with Playwright. Ensures tests focus on observable behaviour, not…

soulcodex/agentic · 79 tokens

compiler-pipeline-internals

The Inkline compiler's end-to-end pipeline — parse → IR → analyze → per-target codegen → print — including the IR contracts, reactivity tracking, target rewrite rules, plugin hooks, the two compile paths, and known sharp edges. Use for any core/ work, or when reviewing it.

inkline/inkline · 67 tokens

create-pr

Author a pull request in the Guild's standard shape — a fixed Summary / Changes / Verification / Notes skeleton that mirrors the review-gate, plus the hard anti-leak rule that no agent @mention or mention:// link ever reaches a public PR. Use whenever you are about to open a PR (e.g. /create-pr), so the PR passes…

inkline/inkline · 79 tokens