reachy_mini_conversation_app: Skill for OpenCode

.opencode/skills/release-notes/SKILL.md

release-notes is a skill for OpenCode from pollen-robotics/reachy_mini_conversation_app. It costs 38 tokens per session (1,540 once invoked), scanned A, original, Apache-2.0.

A release-note writer that reads cached GitHub pull request data and creates a formatted Markdown document for the Reachy Mini Conversation App, a voice app for talking to a Reachy Mini robot.

In plain words
What is it for?
Use it to group pull requests, describe user-facing changes, and produce release notes from saved pull request files.
Why use it?
It removes the need to sort pull requests and rewrite their technical details by hand. It also keeps the notes focused on changes robot users will notice.

Skill for OpenCode

Written for OpenCode: installed under .opencode/.

This is pollen-robotics/reachy_mini_conversation_app's own configuration. It tells OpenCode how to work on reachy_mini_conversation_app 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 reachy_mini_conversation_app configures →

Reuse

Borrowing it

Nothing to install: this file belongs to pollen-robotics/reachy_mini_conversation_app. 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/pollen-robotics/reachy_mini_conversation_app/main/.opencode/skills/release-notes/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/pollen-robotics/reachy_mini_conversation_app

Made for: OpenCode.

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-notes

README.md
[![agentmods](https://agentmods.dev/badge/skills/pollen-robotics/reachy_mini_conversation_app/release-notes/github.svg)](https://agentmods.dev/skills/pollen-robotics/reachy_mini_conversation_app/release-notes)
Your own site
<a href="https://agentmods.dev/skills/pollen-robotics/reachy_mini_conversation_app/release-notes"><img src="https://agentmods.dev/badge/skills/pollen-robotics/reachy_mini_conversation_app/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.

agentmods 80×15 button for release-notes

Your own site · 80×15
<a href="https://agentmods.dev/skills/pollen-robotics/reachy_mini_conversation_app/release-notes"><img src="https://agentmods.dev/badge/skills/pollen-robotics/reachy_mini_conversation_app/release-notes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,540 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.
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 $0.00038 $0.01540
Opus 5.5 $0.00015 $0.00616
Sonnet 5.5 $0.00008 $0.00308
Haiku 4.5 $0.00004 $0.00154

Measured 3d ago against content hash 6383532482b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 3d 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.

.opencode/skills/release-notes/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reachy Mini Conversation App Release Notes

Overview

Generate release notes for reachy_mini_conversation_app from cached PR JSON files. This skill reads PR metadata, categorizes entries, and produces a formatted markdown release notes document.

The app is the real-time voice app that lets people talk to a Reachy Mini robot. Robots install it from a Hugging Face Space, so readers are robot owners first and contributors second: lead with what someone talking to the robot will notice.

Output directory: The prompt will specify the output directory as <output_dir>. All paths below use this placeholder.

Workflow

1. Read PR data

Read all PR JSON files from <output_dir>/tmp/pr_*.json. Each file contains:

{
  "number": 1234,
  "title": "...",
  "author": "username",
  "merged_at": "2026-01-15T10:30:00Z",
  "body": "...",
  "labels": ["highlight"],
  "url": "https://github.com/pollen-robotics/reachy_mini_conversation_app/pull/1234",
  "doc_diffs": [
    {
      "filename": "README.md",
      "status": "modified",
      "patch": "@@ -10,6 +10,10 @@ ..."
    }
  ]
}

The doc_diffs field contains unified diffs for README.md and any .md files under docs/ changed in the PR. It is empty ([]) for PRs with no documentation changes.

2. Identify highlights

A PR should be highlighted if:

  • It has the "highlight" label on GitHub, or
  • You judge it significant enough to deserve a detailed section (e.g., a new thing the robot can do or answer, a noticeable change in how conversations feel, a new UI view, or a change to where user data is stored) even without the label.

Several PRs about the same theme go under one highlight (e.g., local VAD, warmup audio and transcription language all make listening better). Each highlight section follows this structure:

  1. Emoji header: e.g., ## 👂 Faster listening
  2. Prose summary: 2-5 sentences in flowing text. Say what was wrong or missing, what changed, and what the user gets. Use concrete numbers from the PR body when it reports measurements. Only use bullets if the content truly calls for a list (4+ distinct sub-features).
  3. Code examples: only when the PR adds something a developer types (a JSON-RPC method, a profile or tool format, an env var). Cherry-pick from the doc diffs when available.
  4. PR attribution lines: one bullet per PR that contributed to this highlight: - PR title by @author in #1234

Read the full file on GitHub · 119 lines

Files

What ships with it

3 files 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. 3d ago First seen · 119 lines · 38 tokens per session scan A 6383532482b3

Subscribe to this mod's changes

release-notes is a skill published in the GitHub repository pollen-robotics/reachy_mini_conversation_app (353 stars, last pushed yesterday), licensed Apache-2.0. It adds 38 tokens to every session and 1,540 once invoked, about $0.0002 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 2026-11-04.

Related

release-notes compared with skills from other repositories

release-notes next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
release-notespollen-robotics/reachy_mini_conversation_appSkill353yesterdayApache-2.0A38OpenCode
release-announcementpaperclipai/paperclipSkill111kyesterdayMITA42Claude Code, Codex
releasethedotmack/claude-memSkill114kyesterdayApache-2.0A13Claude Code
release-notesphuryn/pm-skillsSkill28k8d agoMITA57Claude Code
multi-agent-release-managerchromium/chromiumSkill25kyesterdayBSD-3-ClauseA27Claude Code, Codex
pack-submitaeonfun/aeonSkill788yesterdayMITA27Claude Code, Codex
updater_guidesiddsachar/row-botSkill1.7kyesterdayApache-2.0A22Claude Code, Codex