seed: Skill for Claude Code

.agents/skills/releasenotes/SKILL.md

releasenotes is a skill for Claude Code, Codex from seed-hypermedia/seed. It costs 15 tokens per session (1,198 once invoked), scanned A, original, Apache-2.0.

A generator for concise release notes that compares two software versions and explains changes from the user's point of view.

In plain words
What is it for?
Use it to write end-user release notes between a starting version and a later version.
Why use it?
It turns developer-oriented changes into short notes that describe what users can do or what problems were fixed.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is seed-hypermedia/seed's own configuration. It tells Claude Code and Codex how to work on seed itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything seed configures →

Reuse

Borrowing it

Nothing to install: this file belongs to seed-hypermedia/seed. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/seed-hypermedia/seed/main/.agents/skills/releasenotes/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/seed-hypermedia/seed

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for releasenotes

README.md
[![agentmods](https://agentmods.dev/badge/skills/seed-hypermedia/seed/releasenotes.svg)](https://agentmods.dev/skills/seed-hypermedia/seed/releasenotes)
Your own site
<a href="https://agentmods.dev/skills/seed-hypermedia/seed/releasenotes"><img src="https://agentmods.dev/badge/skills/seed-hypermedia/seed/releasenotes.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,198 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00015 $0.01198
Opus 5 $0.00008 $0.00599
Sonnet 5 $0.00003 $0.00240
Haiku 4.5 $0.00002 $0.00120

Measured 7d ago against content hash 1b716e99ebd2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

releasenotes 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 7d 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.

.agents/skills/releasenotes/SKILL.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release notes

You are a meticulous release-notes generator that writes for end users, not developers. When invoked as $releasenotes <fromVersion> <toVersion>, do all steps deterministically and return ONLY the final markdown inside a code fence. No extra commentary.

Voice & tone

  • Write every bullet as if explaining to someone who uses the app, not someone who reads the code.
  • Describe what changed for the user, not what code was modified.
  • Use action verbs from the user perspective: "You can now...", "Fix where...", "Improve...".
  • Keep bullets concise but human. No commit-message shorthand, no file paths, no scope tags.

Before / After examples:

  • BAD: Move Join button to header, add members facepile and subscribe box (web)
  • GOOD: Add an easy way to Join a site from the header and make site members more prominent on the homepage
  • BAD: fix(drafts): prefer .json over .md in rebuildFileMap to prevent data loss
  • GOOD: Fix draft changes being lost after restarting the desktop app
  • BAD: fix(daemon): batch PutMany to avoid long-held SQLite write locks
  • GOOD: Improve sync performance for large sites by batching database operations

Classification rules

  • Work in the current git repo.
  • Use only shell and git to gather data.
  • Group commits into: BIG FEATURES, Features, Bug Fixes, Infrastructure (optional).

BIG FEATURES: Commits whose subject/body contains any of: feat!, BREAKING CHANGE, major:, #big (case-insensitive).

Features:

  • Commits starting with feat: or feat(scope): (that are not BIG).
  • Commits without a conventional prefix whose subject clearly describes new user-facing functionality (new UI element, new capability, new user option). Use your judgment. If a user would notice something new, it is a feature.

Bug Fixes:

  • Commits starting with fix: or fix(scope):.
  • Commits whose subject/body contains bug or hotfix.
  • Commits without a conventional prefix that clearly describe broken user-facing behavior being corrected.

Read the full file on GitHub · 124 lines

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. 7d ago First seen · 124 lines · 15 tokens per session scan A 1b716e99ebd2

Subscribe to this mod's changes

releasenotes is a skill published in the GitHub repository seed-hypermedia/seed (56 stars, last pushed today), licensed Apache-2.0. It adds 15 tokens to every session and 1,198 once invoked, about $0.0001 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 2026-08-31.