airi: Skill for Codex

.agents/skills/release-note-writer/SKILL.md

release-note-writer is a skill for Codex from moeru-ai/airi. It costs 84 tokens per session (1,886 once invoked), scanned A, original, MIT.

A guide for turning Git history and other change records into release notes written for users, developers, and contributors. Release notes explain what changed without simply copying commit titles.

In plain words
What is it for?
Use it to prepare grouped release notes from commits, GitHub releases, pull requests, changelogs, and related project history.
Why use it?
Raw commits and technical changelogs can be difficult for readers to understand or may hide changes that matter to everyday users and project contributors.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents); mentions Codex.

This is moeru-ai/airi's own configuration. It tells Codex how to work on airi 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 airi configures →

About the project

AIRI is a self-hosted virtual AI companion that gives an AI character a voice, visual presence, memory, and the ability to interact with games and coding activity. People use it as a personal digital companion on the web, macOS, or Windows, including for voice chat and gameplay. The catalogue add-ons provide workflows for working with the AIRI project.

moeru-ai/airi · 48,961 stars · on GitHub · airi.moeru.ai

Reuse

Borrowing it

Nothing to install: this file belongs to moeru-ai/airi. 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/moeru-ai/airi/main/.agents/skills/release-note-writer/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/moeru-ai/airi

Made for: 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 release-note-writer

README.md
[![agentmods](https://agentmods.dev/badge/skills/moeru-ai/airi/release-note-writer/github.svg)](https://agentmods.dev/skills/moeru-ai/airi/release-note-writer)
Your own site
<a href="https://agentmods.dev/skills/moeru-ai/airi/release-note-writer"><img src="https://agentmods.dev/badge/skills/moeru-ai/airi/release-note-writer/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.

agentmods 80×15 button for release-note-writer

Your own site · 80×15
<a href="https://agentmods.dev/skills/moeru-ai/airi/release-note-writer"><img src="https://agentmods.dev/badge/skills/moeru-ai/airi/release-note-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,886 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
  • Snyk pass 7 Sept 2026
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Rogue Agent · line 141
    Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.
    Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
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 $0.00084 $0.01886
Opus 5 $0.00042 $0.00943
Sonnet 5 $0.00017 $0.00377
Haiku 4.5 $0.00008 $0.00189

Measured 10d ago against content hash f70786b6f62b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

release-note-writer 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 10d 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/release-note-writer/SKILL.md · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release Note Writer

Core Rule

Write release notes in English only. Convert technical history into reader-facing changes grouped by audience and outcome. Do not mirror commit scopes directly.

Required Discovery

Before drafting, gather the release context:

  1. Check the current repo version and tags.
    • Inspect package/version files that already exist in the repo.
    • Inspect recent git tags with git tag --sort=-v:refname.
    • Identify the previous release tag.
  2. Run changelogithub dry output:
    • pnpm dlx changelogithub --dry --from <previous-version>
    • If the command needs network and fails because of sandboxing, request approval and rerun it.
  3. Inspect the generated commit structure and then inspect commits directly.
    • Use git show --stat --oneline <sha> or equivalent targeted commands.
    • Include chore/internal commits when they affect contributor workflow, tooling, builds, CI, local development, docs generation, test infrastructure, or internal packages.
  4. If version boundaries are ambiguous, ask one concise question before drafting.

Audience Structure

Use a compact, aggregated structure. Prefer fewer major sections with useful subheadings over many small scope-based sections. Use multiple heading levels when that makes the audience or product surface clearer.

Recommended order:

  1. Product-facing sections for end users.
  2. ### To developers near the end.
  3. ### To contributors last.
  4. ### Upgrade notes only when action is required.

Product-facing sections can be nested by surface:

  • ### Product updates
  • #### Local
  • #### Cloud
  • #### New providers
  • #### Chat and settings

Do not force every release into these exact headings. Pick headings that make the release easy to scan.

Use a dedicated bug-fix section when fixes include critical regressions, blocked primary workflows, or issues users may scan the notes to confirm. Critical bugs deserve plain, concrete language because users may be checking whether their blocker was fixed. Minor visual, wording, and low-impact cleanup can stay grouped as polish, but do not bury important fixes inside broad product updates.

Read the full file on GitHub · 222 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. 10d ago First seen · 222 lines · 84 tokens per session scan A f70786b6f62b

Subscribe to this mod's changes

release-note-writer is a skill published in the GitHub repository moeru-ai/airi (48,961 stars, last pushed today), licensed MIT. It adds 84 tokens to every session and 1,886 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.