What is multi-lens-review?

A code-review workflow that examines one change from several angles, including defects, requirements, local conventions, domain concepts, and compatibility with replaced code. Code review is the practice of checking changes before they are merged.

Use it to review a diff and report high-confidence findings with scores. It helps check correctness, specification fit, consistency with the codebase, emerging concepts, and old dependencies.

A single review can focus on small style issues and miss broken behavior, a missed requirement, or code that still has dependants. Separate review angles make those different questions explicit.

multi-lens-review — Skill for Claude Code by thoughtbot

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 thoughtbot/rails-consultant --skill multi-lens-review

Clone the repo

git clone --depth 1 https://github.com/thoughtbot/rails-consultant

Made for: Claude Code.

Or install rails-consultant, the plugin that ships this one along with the rest of its 15 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/thoughtbot/rails-consultant/multi-lens-review/github.svg)](https://agentmods.dev/skills/thoughtbot/rails-consultant/multi-lens-review)

Your own site

<a href="https://agentmods.dev/skills/thoughtbot/rails-consultant/multi-lens-review"><img src="https://agentmods.dev/badge/skills/thoughtbot/rails-consultant/multi-lens-review/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/thoughtbot/rails-consultant/multi-lens-review"><img src="https://agentmods.dev/badge/skills/thoughtbot/rails-consultant/multi-lens-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,602 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.

Model	Per session	Once invoked
Fable 5.1	$0.00039	$0.03602
Opus 5.5	$0.00016	$0.01441
Sonnet 5.5	$0.00008	$0.00720
Haiku 4.5	$0.00004	$0.00360

Measured today against content hash 5d0b43c2f832, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

multi-lens-review 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 today.

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.

skills/multi-lens-review/SKILL.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code review

Five reviewers, dispatched in parallel, each reading the same change from a different distance:

Agent	Question
`agents/defects.md`	Is this code wrong — broken, slow, or exploitable?
`agents/spec-fidelity.md`	Did we build what was asked for, and only that?
`agents/conventions.md`	Does this look like the rest of the codebase?
`agents/domains.md`	Is a domain concept trying to emerge here?
`agents/compatibility.md`	Does anything still depend on what this replaced?

They stay separate so the structural reviewer has nothing cheaper to do. One reviewer asked all five questions spends its attention on naming nits, and never reaches "those five files are one domain object in a trenchcoat."

The confidence bar

Every finding carries a confidence out of 100: how sure the reviewer is that it's true and that the author would agree it's worth changing. Below 80, the agent drops it without mentioning it. Print the score with each finding so the author can calibrate how much to argue.

What's scarce in a review is the author's trust, not their reading time.

Workflow

Fix the target — one diff, captured once.
Find the intent the change was supposed to satisfy.
Dispatch the five agents in parallel.
Synthesize into one report.
Offer the fix.

1. Fix the target

$ARGUMENTS may hold a PR number, a branch, paths, or nothing. Decide intent-or-target by what a file says, not where it sits: a file that reads as acceptance criteria is the intent, in docs/specs/ or anywhere else, and a directory or a source path is a target. Ask when a doc argument isn't obviously criteria — reviewing a SPEC file against nothing is a wasted run.

Resolve it to one diff, then capture that diff to a file (mktemp) and hand every agent the same path. If each agent runs its own git diff instead, one reviews the commits while another reviews the working tree, and their findings won't line up with each other or with what the author sees.

Read the full file on GitHub · 161 lines

Files

What ships with it

7 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.

today First seen · 161 lines · 39 tokens per session scan A 5d0b43c2f832

Subscribe to this mod's changes

multi-lens-review is a skill published in the GitHub repository thoughtbot/rails-consultant (29 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 3,602 once invoked, about $0.0002 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 2026-11-07.

Code review claude-code-consulting claude-code-plugin claude-code-rails claude-code-skill claude-code-skills claude-skills

multi-lens-review next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
multi-lens-reviewthoughtbot/rails-consultant	Skill	29	today	MIT	A	39	Claude Code
elixir-wayoliver-kriska/claude-elixir-phoenix	Skill	573	yesterday	MIT	A	55	Claude Code
auditoliver-kriska/claude-elixir-phoenix	Skill	573	yesterday	MIT	A	35	Claude Code
reviewoliver-kriska/claude-elixir-phoenix	Skill	573	yesterday	MIT	A	51	Claude Code
pr-reviewoliver-kriska/claude-elixir-phoenix	Skill	573	yesterday	MIT	A	59	Claude Code
phx-pr-reviewoliver-kriska/claude-elixir-phoenix	Skill	573	yesterday	MIT	A	61	Claude Code, Codex
startoliver-kriska/claude-elixir-phoenix	Skill	573	yesterday	MIT	A	57	Claude Code