review-with-everyone

review-with-everyone is a skill for Claude Code from LaStrada/claude. It costs 161 tokens per session (1,949 once invoked), scanned A, original, MIT.

A code-review skill that sends one code change to several available external review tools and combines their findings into a prioritized report.

In plain words
What is it for?
Getting a panel review of a pull request, branch, staged or unstaged changes, or selected files.
Why use it?
It avoids running and comparing multiple reviews by hand, while checking which reviewers are available and asking for one upload confirmation.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents; mentions Codex.

Part of the review-with plugin — 4 skills, 6 commands shipped together

Good fit Getting a panel review of a pull request, branch, staged or unstaged changes, or selected files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lastrada/claude/review-with-everyone
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 LaStrada/claude --skill review-with-everyone
Clone the repo
git clone --depth 1 https://github.com/LaStrada/claude

Made for: Claude Code.

Or install review-with, the plugin that ships this one along with the rest of its 4 skills, 6 commands.

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-with-everyone

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/lastrada/claude/review-with-everyone"><img src="https://agentmods.dev/badge/skills/lastrada/claude/review-with-everyone.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 161 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,949 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 $0.00161 $0.01949
Opus 5 $0.00081 $0.00975
Sonnet 5 $0.00032 $0.00390
Haiku 4.5 $0.00016 $0.00195

Measured 12d ago against content hash f277aa357479, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

review-with-everyone 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-with/skills/review-with-everyone/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

review-with-everyone

Orchestrate a multi-reviewer "super review": fan out a single resolved diff to the eligible external review CLIs in parallel, then merge their findings into one prioritized report.

This skill owns roster selection, scope resolution, one up-front gate+confirmation, parallel dispatch, and synthesis. It does NOT re-implement any reviewer's CLI flags, model pins, or repo rules — those live in the per-tool skills and stay there. You delegate execution to review-with-codex, review-with-gemini, and review-with-copilot.

The five steps (in order)

  1. Resolve scope — what diff are we reviewing?
  2. Resolve roster + availability preflight — which tools are requested, and which are actually installed?
  3. Gate + ONE confirmation — sensitive paths, public-repo gate, single upload prompt.
  4. Dispatch in parallel — one subagent per eligible tool.
  5. Synthesize — merge into one prioritized report.

1. Resolve scope (dynamic)

Parse the request for the target. Default, if nothing is specified: current branch vs base (BASE..HEAD). Otherwise honor what the user named:

User says Scope
a PR number / URL, or "this PR" that PR's diff + fetch existing PR comments once (passed to all tools)
a branch name, or nothing BASE..HEAD (base = git remote show origin | awk '/HEAD branch/{print $NF}')
"staged" git diff --cached
"unstaged" / "current changes" / "what I have" git diff (or git diff HEAD for both staged+unstaged)
one or more files restrict the diff to those paths
a commit sha git show <sha>

Compute the diff once here. All tools review the exact same payload. Full parsing detail: references/scope-roster.md.

2. Resolve roster + availability preflight (dynamic)

  • "super review" / "review with all" / "review with everyone" → all three eligible.
  • "review with all gemini and copilot" (or any explicit subset) → only the named tools.

Availability preflight. This skill orchestrates the per-tool skills; it does NOT bundle their CLIs. A tool can run only if its CLI is installed. Check the requested roster:

Read the full file on GitHub · 98 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. 12d ago First seen · 98 lines · 161 tokens per session scan A f277aa357479

Subscribe to this mod's changes

review-with-everyone is a skill published in the GitHub repository LaStrada/claude (2 stars, last pushed 2mo ago), licensed MIT. It adds 161 tokens to every session and 1,949 once invoked, about $0.0008 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 2026-08-31.