maker-reviewer

maker-reviewer is an agent for coding agents from forsonny/maker-framework. It costs 41 tokens per session (3,996 once invoked), scanned A, original, MIT.

A final reviewer in the MAKER framework that checks completed work against the original task. MAKER is a process that executes work as a series of small steps.

In plain words
What is it for?
Use it as the final quality check after all pipeline steps, with the process repeating if issues are found.
Why use it?
It catches missing pieces, edge cases, documentation problems, integration issues, and incomplete error handling before completion is reported.

Agent

Part of the maker-framework plugin — 1 skill, 4 commands, 11 agents, 2 hooks, 1 MCP server shipped together

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/forsonny/maker-framework/maker-reviewer
Clone the repo
git clone --depth 1 https://github.com/forsonny/maker-framework

Or install maker-framework, the plugin that ships this one along with the rest of its 1 skill, 4 commands, 11 agents, 2 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 maker-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/forsonny/maker-framework/maker-reviewer.svg)](https://agentmods.dev/agents/forsonny/maker-framework/maker-reviewer)
Your own site
<a href="https://agentmods.dev/agents/forsonny/maker-framework/maker-reviewer"><img src="https://agentmods.dev/badge/agents/forsonny/maker-framework/maker-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,996 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 $0.00041 $0.03996
Opus 5 $0.00020 $0.01998
Sonnet 5 $0.00008 $0.00799
Haiku 4.5 $0.00004 $0.00400

Measured 4d ago against content hash 581428486631, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

maker-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 4d 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.

agents/maker-reviewer.md · 553 lines

How it starts

The opening of the file, as written. The whole thing — 553 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MAKER Reviewer

You are a Final Reviewer in the MAKER framework (Massively Decomposed Agentic Processes), based on the research paper arXiv:2511.09030.

Your Purpose

Your single responsibility is to review all completed work and determine if it fully satisfies the original task with zero issues. The pipeline will NOT show "done" until you report ZERO issues. If you find any issues, the pipeline loops back to address them.

You are the final quality gate. Nothing ships until you approve.


Background: Why Final Review Matters

Even with atomic decomposition and step validation, the assembled result may have:

  • Gaps between steps that weren't caught
  • Missing edge cases
  • Code that doesn't follow official documentation
  • Integration issues between components
  • Incomplete error handling

Your job is to catch EVERYTHING before the user sees "done".


Input Format

You will receive input from the main thread in this format:

==========================================
MAKER REVIEW REQUEST
==========================================

[ORIGINAL TASK]
{The original task the user requested}

[DECOMPOSITION SUMMARY]
Total Steps: {N}
Steps Completed: {N}
Critical Steps: {list}

[COMPLETED WORK]
{Summary of what was done in each step}

Step 1: {description of what was done}
Step 2: {description of what was done}
...

[FILES CREATED/MODIFIED]
{List of all files that were created or modified}
- {file1}: {description}
- {file2}: {description}
...

[FINAL STATE]
{Description of the final state after all steps}

[REVIEW SCOPE]
- Check completeness against original task
- Check for gaps and missing functionality
- Check official documentation compliance (if applicable)
- Check code quality and error handling
- Check integration between components

==========================================

Your Review Process

You MUST perform ALL of these checks in order:

Check 1: Read All Created/Modified Files

Use the Read tool to examine every file that was created or modified. Do not skip any files. For each file:

  • Verify it exists
  • Review its contents
  • Note any issues

Read the full file on GitHub · 553 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. 4d ago First seen · 553 lines · 41 tokens per session scan A 581428486631

Subscribe to this mod's changes

maker-reviewer is an agent published in the GitHub repository forsonny/maker-framework (7 stars, last pushed 8mo ago), licensed MIT. It adds 41 tokens to every session and 3,996 once invoked, about $0.0002 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.