agentmods.dev

review:meat-proxy

review:meat-proxy is a skill for Claude Code from bendrucker/claude. It costs 21 tokens per session (1,518 once invoked), scanned A, original, MIT.

A reply-drafting aid for review comments on work that someone passed on from an AI without checking. It produces a short response that asks the original author to explain and defend the change.

In plain words
What is it for?
Use it to draft questions for a pull request, merge request, or document review when the author needs to demonstrate understanding of their own change.
Why use it?
It keeps the reviewer from doing the author's thinking and writing the work themselves. It also makes clear that the draft is not posted or submitted automatically.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents.

Part of the review plugin — 4 skills shipped together

not rated 18repo changed 12d ago A scan 21 tokens original MIT

Good fit Use it to draft questions for a pull request, merge request, or document review when the author needs to demonstrate understanding of their own change.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bendrucker/claude/meat-proxy
View source ↗ bendrucker/claude
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add bendrucker/claude --skill meat-proxy
Clone the repo
git clone --depth 1 https://github.com/bendrucker/claude

Made for: Claude Code.

Or install review, the plugin that ships this one along with the rest of its 4 skills.

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 review:meat-proxy

README.md
[![agentmods](https://agentmods.dev/badge/skills/bendrucker/claude/meat-proxy/github.svg)](https://agentmods.dev/skills/bendrucker/claude/meat-proxy)
Your own site
<a href="https://agentmods.dev/skills/bendrucker/claude/meat-proxy"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/meat-proxy/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 review:meat-proxy

Your own site · 80×15
<a href="https://agentmods.dev/skills/bendrucker/claude/meat-proxy"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/meat-proxy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,518 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 $0.00021 $0.01518
Opus 5.5 $0.00008 $0.00607
Sonnet 5.5 $0.00004 $0.00304
Haiku 4.5 $0.00002 $0.00152

Measured 12d ago against content hash bcb65d440616, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

review:meat-proxy 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 12d 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.

plugins/review/skills/meat-proxy/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Meat Proxy

Target and instructions: $ARGUMENTS

I suspect the author of this artifact relayed model output without reading or checking it, and can't explain or defend it. When that holds, each round of review feedback goes back into the model, so the reviewer ends up doing the authoring. Your job is to hand the work back: draft a short reply in my voice that makes the author engage with their own change, and keep everything else private to me. A good reply asks things the author must think about to answer, and leaves the finding to them.

You draft. Don't post until I tell you to. When I do, stage the draft unpublished where the platform supports it (a GitLab draft note, a pending GitHub review), and record outcome in the state file then.

Inputs

  • Target: the first argument. A PR or MR URL, a doc link, or pasted text. Fetch PRs through gh, MRs through glab (load gitlab:merge-request for GitLab), and docs through whatever reads them.
  • Instructions: everything after the target, optional. They can carry any of:
    • A reaction: my gut call about what's wrong. Test it against the artifact before using it. When it holds, frame the questions around it. When it doesn't, frame them around what does hold and say why in the private notes.
    • Questions for you. Answer them in the private notes.
    • Sources to consult: a ticket, a chat thread, my earlier review. Read them alongside the artifact.
  • Prior direction: what I've already told the author about this change, in the thread or in those sources. Anchor the draft's questions in it, and treat what it settles as settled.

State

Keep one state file per target at ${CLAUDE_PLUGIN_DATA}/meat-proxy/<slug>.md. Read and write it with the Read, Write, and Edit tools. Build the slug from the target: owner-repo-123 for a PR or MR, a short kebab-case name for a doc or pasted text.

When the file exists, this is a follow-up round. Read it first, then follow Follow-Up Rounds.

Read the full file on GitHub · 103 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. 12d ago Changed · +12 lines bcb65d440616
  2. 1mo ago First seen · 91 lines · 21 tokens per session scan A d759950290b3

Subscribe to this mod's changes

review:meat-proxy is a skill published in the GitHub repository bendrucker/claude (18 stars, last pushed today), licensed MIT. It adds 21 tokens to every session and 1,518 once invoked, about $0.0001 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 2026-10-08.

Claude CodeCode reviewWriting and docsclaude-code-plugin
Related

review:meat-proxy compared with skills from other repositories

review:meat-proxy next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
review:meat-proxybendrucker/claudeSkill18todayMITA21Claude Code
reviewSethGammon/CitadelSkill9284d agoMITA17Claude Code
critical-code-reviewerposit-dev/skillsSkill5617d agoMITA67Claude Code
brooks-sweephyhmrright/brooks-lintSkill1.6ktodayMITA178Claude Code
pr-reviewnitinjain999/platform-skillsSkill71yesterdayApache-2.0A81Claude Code
skill-distilleriliaal/whetstoneSkill36todayMITA91Claude Code
review-depthjszmajda/lidSkill118todayMITA93Claude Code