voicebox: Skill for Claude Code

.agents/skills/triage-prs/SKILL.md

triage-prs is a skill for Claude Code, Codex from jamiepine/voicebox. It costs 80 tokens per session (3,228 once invoked), scanned A, original, MIT.

A skill for sorting and processing open GitHub pull requests before a software release. It labels each request as required, possible, replaced, or postponed, then records and carries out the resulting merge plan.

In plain words
What is it for?
Use it before a minor or major release to review many open pull requests, rebase and merge selected ones in batches, apply post-merge work, and close requests that no longer apply.
Why use it?
It turns a large backlog into a tracked decision list and helps a maintainer merge the selected changes without losing follow-up tasks or contributor credit.

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 jamiepine/voicebox's own configuration. It tells Claude Code and Codex how to work on voicebox 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 voicebox configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is git worktree add ../voicebox-pr-review -b pr-review-<VERSION> main.

About the project

Voicebox is a local AI voice studio that clones voices, generates speech, and turns spoken input into text on a computer. People use it for dictation, voice creation, and giving MCP-compatible agents spoken output. The catalogue add-ons support workflows around operating Voicebox.

jamiepine/voicebox · 52,384 stars · on GitHub · voicebox.sh

Reuse

Borrowing it

Nothing to install: this file belongs to jamiepine/voicebox. 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/jamiepine/voicebox/main/.agents/skills/triage-prs/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/jamiepine/voicebox

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 triage-prs

README.md
[![agentmods](https://agentmods.dev/badge/skills/jamiepine/voicebox/triage-prs.svg)](https://agentmods.dev/skills/jamiepine/voicebox/triage-prs)
Your own site
<a href="https://agentmods.dev/skills/jamiepine/voicebox/triage-prs"><img src="https://agentmods.dev/badge/skills/jamiepine/voicebox/triage-prs.svg" alt="Measured on agentmods" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,228 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 $0.00080 $0.03228
Opus 5 $0.00040 $0.01614
Sonnet 5 $0.00016 $0.00646
Haiku 4.5 $0.00008 $0.00323

Measured 7d ago against content hash 0a53c9151af4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

triage-prs 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.agents/skills/triage-prs/SKILL.md · 300 lines

How it starts

The opening of the file, as written. The whole thing — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Triage PRs

Goal

Turn a backlog of open PRs into a shipped set of merges in a single focused session. Produce a tracked, resumable plan (<VERSION>_PR_TRIAGE.md), then work it — rebasing where needed, merging in isolation-safe batches, applying post-merge follow-ups, and closing superseded or partially-applicable PRs with credit to their authors.

This skill pairs with draft-release-notes and release-bump: triage first, then draft notes against the new main, then cut the release.

When to use

  • Before a minor or major release when 10+ open PRs have accumulated
  • When you want to unblock merging without losing the narrative of what's landing
  • When you know you can't personally review every PR deeply, but need to land the critical subset fast

Prerequisites

  • gh CLI authenticated against the repo
  • A dedicated worktree for PR review (avoid contaminating main with checkouts of contributor branches)
  • Clarity on the target version — the triage doc is named after it (e.g. 0.4.0_PR_TRIAGE.md)

Workflow

1. Set up an isolated PR-review worktree

git worktree list  # check for stale ones first
git worktree prune
git worktree add ../voicebox-pr-review -b pr-review-<VERSION> main

Keep the main worktree for release-prep work (changelog drafts, direct-to-main follow-ups). Keep the review worktree for gh pr checkout — each checkout moves HEAD to a contributor branch, which you don't want to do in the main worktree.

2. Gather metadata for every open PR

gh pr list --state open --limit 50 --json \
  number,title,author,isDraft,mergeable,mergeStateStatus,files,additions,deletions,reviewDecision,statusCheckRollup,maintainerCanModify \
  --jq '.[] | {num: .number, title, author: .author.login, mergeable, state: .mergeStateStatus, canModify: .maintainerCanModify, changes: "+\(.additions)/-\(.deletions)", files: [.files[].path]}'

You want, for each PR:

  • Size (+additions/-deletions)
  • Mergeable state (CLEAN, UNSTABLE, DIRTY = conflicts, UNKNOWN = GitHub still computing)
  • Whether maintainer edits are allowed on the branch (needed later if you rebase for the author)
  • File paths touched (helps spot overlaps between PRs)

Read the full file on GitHub · 300 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 · 300 lines · 80 tokens per session scan A 0a53c9151af4

Subscribe to this mod's changes

triage-prs is a skill published in the GitHub repository jamiepine/voicebox (52,384 stars, last pushed 29d ago), licensed MIT. It adds 80 tokens to every session and 3,228 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.