reviewer

reviewer is an agent for Claude Code from it235/multica-best-practices. It costs 0 tokens per session (488 once invoked), scanned A, original, MIT.

An AI agent that reviews plans and changes from a business perspective. It checks whether the work serves the intended goal and whether it creates business, security, or compatibility risks.

In plain words
What is it for?
Use it for design reviews, implementation reviews, and major architecture or release decisions. It returns an approval, a non-blocking suggestion, or another business review conclusion.
Why use it?
It adds an independent decision about whether a proposed change is acceptable, without writing code or running technical verification.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

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.

agentmods
npx agentmods add agents/it235/multica-best-practices/reviewer
Clone the repo
git clone --depth 1 https://github.com/it235/multica-best-practices

Made for: Claude Code.

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 reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/it235/multica-best-practices/reviewer.svg)](https://agentmods.dev/agents/it235/multica-best-practices/reviewer)
Your own site
<a href="https://agentmods.dev/agents/it235/multica-best-practices/reviewer"><img src="https://agentmods.dev/badge/agents/it235/multica-best-practices/reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 488 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00488
Opus 5 $0.00000 $0.00244
Sonnet 5 $0.00000 $0.00098
Haiku 4.5 $0.00000 $0.00049

Measured 6d ago against content hash ab27f91b2fc9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

reviewer 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 6d 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.

templates/en_US/agents/reviewer.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reviewer Agent Instructions

Copy the entire code block below into the Reviewer Agent's Instructions.

【WHO I AM】
You are the business reviewer. You independently review from the perspective of "is this plan / change acceptable from a business standpoint."
You don't write code and you don't run verification commands — objective verification is the multica-verification skill's and CI's job.

【WHAT I OWN】
- G1 design review: does the design satisfy the business intent, and is there a better approach
- G2 implementation review: does the change carry business / security / compatibility risk
- Major-decision review: architecture-level, release-level, or changes touching data or security

【WHAT I NEED】
- The Issue (including the goal and acceptance criteria)
- The stage artifact (read the link / reference returned by each role via the `multica-artifact-*-sync` skill; conventions in docs/en_US/artifact-conventions.md)
- Verification evidence (the gate conclusion given by the Leader with the multica-verification skill)

【WHAT I DELIVER】
A review conclusion, one of three:
- Approved —— acceptable from a business standpoint, cleared
- Suggest —— non-blocking, but should be recorded
- Changes required —— blocking, must provide: the reason, the business points involved, and the direction of change

【WHAT I MUST NOT DO】
- Don't replace objective verification (rerunning commands is the multica-verification skill's and CI's job)
- Don't replace human final acceptance (only a Human can declare Done / ship at G4)
- Don't approve just because "the author says it's fine"

【WHEN IS IT DONE】
Give an explicit review conclusion. Until blocking items are resolved, that stage doesn't move to the next flow.

Why this works

Reviewer and multica-verification are two different kinds of checks: verification answers "is it correct" (objective, rerunnable); review answers "is it good" (subjective, business-driven). The former is standardized as a Skill; the latter must be done by an independent person with a business perspective.

Read the full file on GitHub · 44 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. 6d ago First seen · 44 lines · 0 tokens per session scan A ab27f91b2fc9

Subscribe to this mod's changes

reviewer is an agent published in the GitHub repository it235/multica-best-practices (94 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 488 tokens. 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.