Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add livlign/claude-skills/plugin install pr-voiceWrote 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.
[](https://agentmods.dev/skills/livlign/claude-skills/pr-voice)<a href="https://agentmods.dev/skills/livlign/claude-skills/pr-voice"><img src="https://agentmods.dev/badge/skills/livlign/claude-skills/pr-voice/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.
<a href="https://agentmods.dev/skills/livlign/claude-skills/pr-voice"><img src="https://agentmods.dev/badge/skills/livlign/claude-skills/pr-voice.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00116 | $0.03538 |
| Opus 5.5 | $0.00046 | $0.01415 |
| Sonnet 5.5 | $0.00023 | $0.00708 |
| Haiku 4.5 | $0.00012 | $0.00354 |
Grade A, and why
pr-voice 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pr-voice
Solo maintainers ship fast and PR bodies suffer: "fix stuff", an empty template, a title that's the branch name. A generic rewrite makes it worse in a different way — every assistant-written PR comes out as Summary / Changes / Testing with a bullet per file and a confident "All tests pass", which reads as foreign in a repo whose PRs are two plain sentences, and is wrong when nobody ran the tests.
This skill writes the description the way this repo already writes them, measured from what it actually merged, and says only what the diff, commits, and linked issues support.
Two things carry the quality, in this order:
- Facts from the change, not from imagination. The diff is the source of truth. Motivation the diff can't show is asked for or left out, never made up.
- Voice from the measured history, not from taste.
scripts/pr-corpus.pyturns merged PRs into numbers (title shape, length per diff size, recurring headings). The draft is checked against them before anyone sees it.
Phases
- Target — pick operating mode, resolve which PR (or branch) is being described, collect its facts.
- Voice — profile the repo's merged history, read the exemplars and the PR template.
- Draft — write title + body, then self-check against the profile and the fact ledger.
- Apply — show before/after; write it to GitHub only on explicit confirmation.
Phase 1 — Target
1.1 Operating mode (ask first)
Same three modes as repo-visuals and readme-doctor, via AskUserQuestion. Mode changes how many decisions are surfaced; it never skips the fact check (§3.3) or the apply confirmation (§4.2).
| Mode | What the user decides | Typical back-and-forths |
|---|---|---|
| Auto | nothing until the final apply confirmation | 1 |
| Semi-auto (default) | answers to open "why" questions (§1.4), the apply | ~2 |
| Manual | voice scope, which exemplars to model, each open question, the draft, the apply | 4–6 |
If the user's request already says "just do it" or names a mode, don't ask.
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.
- yesterday First seen · 202 lines · 116 tokens per session scan A 30c0e699b2d1
pr-voice is a skill published in the GitHub repository livlign/claude-skills (20 stars, last pushed 2d ago), licensed MIT. It adds 116 tokens to every session and 3,538 once invoked, about $0.0005 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 2026-10-16.
Other skills, from other repositories
pwp-code-review
Systematic code review protocol — review code with rigor and specificity. Use this skill whenever the user asks you to review code, check a PR, audit a file, look over changes, or give feedback on implementation quality. Also use when they say 'review this', 'is this code good', 'check my work', 'what do you think of…
pwp-refactor
Safe refactoring protocol — restructure code without breaking behavior. Use this skill whenever the user asks to refactor, restructure, reorganize, clean up, simplify, or decompose code. Also use when they say 'this file is too big', 'too much duplication', 'split this up', 'make this cleaner', 'reduce complexity', or…
review-checklist
Code review standards and checklist for the code-reviewer agent.
boundaries
Analyze Phoenix context boundaries and module coupling via mix xref. Use when checking cross-context calls, validating dependencies, before splitting modules, or reviewing architecture.
pr-threads-address
Address PR review feedback by systematically working through every unresolved PR review thread on the current branch's PR - analyze each comment, make the requested code changes (with tests where useful), commit, and optionally reply and resolve.
r-tidyverse-style
Use when the user asks to review or clean up R code for tidyverse style, standardize formatting or names, remove redundant comments or wrappers, or make a behavior-preserving style pass. Also use when writing substantial new R package code if the user requests tidyverse style or the package already follows it. Not for…