draft-release-notes

A guide for preparing release-notes pages for NeMo Relay by comparing two release branches and checking repository evidence. Release notes summarize changes users should know about.

In plain words
What is it for?
Use it when preparing or reviewing release notes for a new version. It helps identify candidate changes and verify breaking changes, migrations, features, and support limits.
Why use it?
It reduces the risk of publishing claims that are not supported by the code or public documentation. It also separates complete release history from the shorter website summary.

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/nemo-relay/draft-release-notes
Any agent
npx skills add NVIDIA/NeMo-Relay --skill draft-release-notes
Clone the repo
git clone --depth 1 https://github.com/NVIDIA/NeMo-Relay

Made for: Claude Code, Codex.

Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 620 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 $0.00056 $0.00620
Opus 5 $0.00028 $0.00310
Sonnet 5 $0.00011 $0.00124
Haiku 4.5 $0.00006 $0.00062

Measured 2d ago against content hash b8acfa47bff9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

draft-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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/collect_release_evidence.py), 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/draft-release-notes/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Draft Release Notes

Draft the three documentation-site release-notes pages from verified repository evidence. Keep complete, PR-by-PR release history in GitHub Releases.

Gather Evidence

Run the read-only helper with explicit release refs and the target minor version:

python3 .agents/skills/draft-release-notes/scripts/collect_release_evidence.py \
  --previous release/<previous-major>.<previous-minor> \
  --current HEAD \
  --version <major>.<minor>

The report verifies both refs, compares their release-notes trees, identifies version text currently present in those pages, and groups commits into review candidates. Treat the groups as an evidence index, not publication-ready copy.

Workflow

  1. Confirm the target release version from the release branch and package metadata. Preserve unrelated working-tree changes.
  2. Run the helper. It reports an absent prior release-notes directory without failing, which is expected for early release branches.
  3. Verify each candidate claim in the changed public docs, API types, command help, or source before including it. Prioritize breaking changes, migrations, user-visible features, and ongoing support limitations.
  4. Update only these pages unless the release changes their route or entry points:
    • docs/about-nemo-relay/release-notes/index.mdx
    • docs/about-nemo-relay/release-notes/highlights.mdx
    • docs/about-nemo-relay/release-notes/known-issues.mdx
  5. Keep the existing page roles:
    • index.mdx gives the current-release summary, compatibility notes, scope, and curated feature links.
    • highlights.mdx groups notable changes by user-facing theme.
    • known-issues.mdx records current limitations, compatibility migrations, current-release fixes, and the complete fixed-item history recorded in earlier release-note pages. Preserve every prior fixed-item bullet under release-labelled subsections; do not summarize, deduplicate, or omit it. GitHub Releases remains the complete PR-by-PR history.
  6. Preserve MDX front matter and the JSX SPDX comment. State the full history is available in GitHub Releases; do not create a changelog or GitHub Release body from this skill.

Read the full file on GitHub · 66 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 · 66 lines · 56 tokens per session scan A b8acfa47bff9

Subscribe to this mod's changes

draft-release-notes is a skill published in the GitHub repository NVIDIA/NeMo-Relay (132 stars, last pushed 3d ago), licensed Apache-2.0. It adds 56 tokens to every session and 620 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.

Related

Other skills, from other repositories