Review changes (multi-agent)

Review changes (multi-agent) is a skill for Claude Code, Codex from AuraVixStudio/caelo. It costs 20 tokens per session (354 once invoked), scanned A, original, Apache-2.0.

A process for reviewing local code changes by sending separate read-only reviewers to different areas and combining their findings. Each finding includes a file and line reference plus a short explanation.

In plain words
What is it for?
Use it to review a current diff or branch, divide changed files among reviewers, and produce one prioritized list of issues without applying fixes.
Why use it?
It helps spot correctness bugs, security issues, and maintainability problems across a branch without allowing reviewers to modify the code. Grouping the work by area makes a large change easier to inspect.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Use it to review a current diff or branch, divide changed files…

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

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 Review changes (multi-agent)

README.md
[![agentmods](https://agentmods.dev/badge/skills/auravixstudio/caelo/review.svg)](https://agentmods.dev/skills/auravixstudio/caelo/review)
Your own site
<a href="https://agentmods.dev/skills/auravixstudio/caelo/review"><img src="https://agentmods.dev/badge/skills/auravixstudio/caelo/review.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 354 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 $0.00020 $0.00354
Opus 5 $0.00010 $0.00177
Sonnet 5 $0.00004 $0.00071
Haiku 4.5 $0.00002 $0.00035

Measured 7d ago against content hash 1d1c2553fe2b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

Review changes (multi-agent) 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.

caelo_core/skills/builtin/review/SKILL.md · 30 lines

What it actually says

Review changes (multi-agent)

Use this to get a thorough, read-only review of the current local changes (or a branch) by fanning out to reviewer subagents. Reviewers do not modify anything.

Steps

  1. Scope the diff. Identify what changed: run git status / git diff --stat (or git diff <base>...HEAD) with run_command, or glob/list_dir if there is no git. Build the list of changed files and group them by area.
  2. Delegate reviewers. delegate a reviewer per area (parallel for independent areas). Tell each reviewer the exact files to read and the relevant changed lines, and ask for correctness bugs, security issues, and quality/maintainability concerns — each with a file:line reference and a short rationale.
  3. Consolidate. Merge the returned findings, drop duplicates, and sort by severity.
  4. Report. Present one prioritized list to the user. Do not fix anything here — this skill only reviews. (If the user wants fixes, switch to the implement loop.)

Notes

  • Reviewers are READONLY (no run_command); gather any command output (e.g. the diff) yourself and pass the relevant context into each subagent's task.
  • Keep each reviewer's scope tight so its summary stays actionable.
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 · 30 lines · 20 tokens per session scan A 1d1c2553fe2b

Subscribe to this mod's changes

Review changes (multi-agent) is a skill published in the GitHub repository AuraVixStudio/caelo (23 stars, last pushed 25d ago), licensed Apache-2.0. It adds 20 tokens to every session and 354 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

api-reviewer

Use when the user asks to review or change an HTTP, RPC, event, CLI, or SDK API contract. Inspect routes, schemas, authorization, errors, compatibility, and consumers before editing, then verify request and response behavior with focused tests.

lfyxhappy/lfcode · 53 tokens

pull-request-author

Use when the user asks to prepare, update, audit, or submit a pull request. Inspect repository contribution rules, branch state, diff, tests, and the target base first; create a focused reviewable change description and do not commit, push, or open a hosted pull request without explicit authorization.

lfyxhappy/lfcode · 64 tokens

refactor-engineer

Use when the user requests a behavior-preserving code refactor, cleanup, extraction, consolidation, or architectural simplification. Map all references and contracts before editing, keep the change scoped, and prove behavior with focused tests and type checks.

lfyxhappy/lfcode · 52 tokens

code-reviewer

A code-review guide for examining a change and its surrounding behavior for bugs, regressions, security risks, compatibility problems, and missing tests. A code review checks proposed changes before they are accepted.

lfyxhappy/lfcode · 82 tokens

agentbro-pr-merge

Use when reviewing, fixing CI for, approving workflows for, or merging AgentBro pull requests into dev/main, especially external contributor PRs where contributor attribution matters.

shirenchuang/agentbro · 38 tokens

code-reviewer

Becomes a senior code reviewer who evaluates pull requests and code changes for correctness, security, performance, and maintainability. Use when the user asks for code review, PR feedback, code quality assessment, or merge readiness evaluation. Do NOT use when writing new code, debugging runtime errors, designing…

FerroxLabs/wayland · 75 tokens