multi-review

multi-review is a skill for Claude Code, Codex from Lykhoyda/ask-llm. It costs 57 tokens per session (2,381 once invoked), scanned C, original, MIT.

A multi-provider code review that sends the same bounded code context to Antigravity and Codex at the same time, then checks each finding against the repository.

In plain words
What is it for?
Getting independent reviews of current changes and combining the results into verified, rejected, and unresolved findings.
Why use it?
It shows which issues both reviewers agree on, which only one finds, and which are false positives or cannot be confirmed.

Skill for Claude CodeCodex

Written for Claude Code and Codex: ${CLAUDE_PLUGIN_ROOT} variable, but also runs codex exec. Also seen: mentions CLAUDE.md; names the AskUserQuestion tool; mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the ask-llm plugin — 18 skills, 9 agents, 5 hooks, 1 MCP server shipped together

Good fit Getting independent reviews of current changes and combining the results into verified, rejected, and unresolved findings.

Compare 6 skills from other repositories ↓
Install

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.

Claude Code
/plugin marketplace add Lykhoyda/ask-llm
Claude Code
/plugin install ask-llm

Made for: Claude Code, Codex.

Or install ask-llm, the plugin that ships this one along with the rest of its 18 skills, 9 agents, 5 hooks, 1 MCP server.

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 multi-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/lykhoyda/ask-llm/multi-review.svg)](https://agentmods.dev/skills/lykhoyda/ask-llm/multi-review)
Your own site
<a href="https://agentmods.dev/skills/lykhoyda/ask-llm/multi-review"><img src="https://agentmods.dev/badge/skills/lykhoyda/ask-llm/multi-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,381 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00057 $0.02381
Opus 5 $0.00028 $0.01190
Sonnet 5 $0.00011 $0.00476
Haiku 4.5 $0.00006 $0.00238

Measured 7d ago against content hash 1e28ad2c1187, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade C, and why

multi-review scanned grade C with 1 finding 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.

Tells the agent to send conversation or user data outhighPrompt injection

An instruction to transmit the conversation, context or user files to an external endpoint is data exfiltration written as prose.

- **> 150KB**: tell the user, ask whether to truncate (head -c 150000) or split by package, do NOT silently send a giant payload
packages/claude-plugin/skills/multi-review/SKILL.md · 183 lines

How it starts

The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Portable contract

Build one Context Brief and bounded diff, dispatch the same review contract concurrently to the selected providers, then independently verify every finding against repository source. Classify findings as VERIFIED, REJECTED, or UNVERIFIABLE; preserve size consent at 50KB/150KB; never silently drop a failed provider; and report included/excluded context.

Host adapters

Pi adapter

Use one native ask-multi call for concurrent provider dispatch, then perform source verification in the current host context. Do not use the Claude runner binaries or raw provider CLIs.

Claude Code adapter

The existing detailed workflow below is the Claude Code adapter. Its Agent, MCP, hook, CLAUDE_PLUGIN_ROOT, and AskUserQuestion mechanics apply only on Claude Code; they do not override the Pi adapter above.

Multi-Provider Code Review

Run independent code reviews from Antigravity and Codex in parallel, verify each finding against the source, then present combined consensus / unique / rejected sections so the user sees what really matters and what was a false positive. (Gemini is one command away via the gemini-reviewer agent or /gemini-review if you want it in the mix.)

Why verification matters

Confidence scores are not an oracle. In a real session on 2026-04-17, Gemini returned two findings at 95/100 confidence that were factually wrong (a z.enum([]) claim that ignored an existing fallback, and an "MCP SDK doesn't support outputSchema" claim that was contradicted by the actual .d.ts). Both would have caused a mis-fix if accepted at face value. Always verify before presenting.

Two kinds of verification — pick the right skill

This skill verifies review findings — the bugs each provider claims it found. Phase 3 reads the file at the cited line and checks whether each finding is real before presenting it.

That is different from verifying assistant claims — the statements the assistant made in its prior turn ("I added retry logic," "I bumped the threshold to 16384"). For that, use /codex-verify. It dispatches the codex-verifier agent, decomposes the assistant's last message into atomic claims, and proves or disproves each with deterministic evidence. It returns a CONFIDENCE grade on a five-point ladder (PERFECT | VERIFIED | PARTIAL | FEEDBACK | FAILED) — PARTIAL and FAILED are first-class verdicts, surfacing gaps in your verification harness rather than hiding them under a confident-looking number.

Read the full file on GitHub · 183 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 · 183 lines · 57 tokens per session scan C 1e28ad2c1187

Subscribe to this mod's changes

multi-review is a skill published in the GitHub repository Lykhoyda/ask-llm (17 stars, last pushed 4d ago), licensed MIT. It adds 57 tokens to every session and 2,381 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent to send conversation or user data out). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

ocr

AI-powered multi-agent code review. Simulates a team of Principal Engineers reviewing code from different perspectives. Use when asked to review code, check a PR, analyze changes, or perform code review.

spencermarx/open-code-review · 44 tokens

OCR Review-to-Approval Loop

Drive a PR to an approved code review by looping OCR's multi-agent review and address steps. Runs /ocr:review then /ocr:address repeatedly until the review verdict is APPROVE, then one final /ocr:address for leftover suggestions, posting every review and every address round to the GitHub PR as comments. Use when the…

spencermarx/open-code-review · 178 tokens

repo-doctor

USE WHEN inheriting a legacy repo, when user asks "what's missing for AI-first work here?", "is this repo agent-ready?", "audit my repo", "is anything out of sync with the code?", or when the bare-repo-nudge / cheatsheet hook suggests a checkup. Read-only AI-readiness audit — scores 24 dimensions across Foundation…

Filip-Podstavec/claude-leverage · 316 tokens

security-review

USE BEFORE committing security-sensitive changes (auth, crypto, routes, user-input handling, secret loading, templates), or when the security-nudge Stop hook suggests it. Audits the current diff for OWASP-Top-10-shaped issues + deps typosquatting. Read-only. Delegates to the security-reviewer Sonnet subagent shipped…

Filip-Podstavec/claude-leverage · 91 tokens

swarm

Run a multi-agent audit of a codebase by spawning specialized parallel subagents (security, performance, tests, architecture, dead-code), then synthesize their findings into a single prioritized action plan. Use this whenever the user runs /swarm, asks to "audit the repo," "review this codebase," "find issues across…

Zintellix/Claude-Skills · 138 tokens

readme-doctor

Audit a GitHub repo's README against best-practice patterns and produce a prioritized punch list of fixes. Runs a structured review covering hero presence, install-to-first-success length, "what is this in one sentence" clarity, audience-jargon match, scannability, and drift signals (stale versions, dead links, badge…

livlign/claude-skills · 88 tokens