maker-checker

maker-checker is a skill for Claude Code from bjorn-ingmanson/thefroject-plugins. It costs 46 tokens per session (608 once invoked), scanned A, original, MIT.

A review process in which one agent creates an output and a separate agent checks it against defined criteria. They repeat the process until the checker approves or the allowed attempts are used.

In plain words
What is it for?
Use it for code reviews, content editing, or other work that needs a separate validation step before it is accepted.
Why use it?
It provides an independent quality check instead of relying only on the agent that made the work. The criteria can cover required content, prohibited content, clarity, compilation, tests, or project conventions.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the thefroject-customer-success plugin — 47 skills, 11 commands shipped together

Good fit Use it for code reviews, content editing, or other work that needs a separate validation step before it is accepted.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bjorn-ingmanson/thefroject-plugins/maker-checker
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 bjorn-ingmanson/thefroject-plugins --skill maker-checker
Clone the repo
git clone --depth 1 https://github.com/bjorn-ingmanson/thefroject-plugins

Made for: Claude Code.

Or install thefroject-customer-success, the plugin that ships this one along with the rest of its 47 skills, 11 commands.

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-checker

README.md
[![agentmods](https://agentmods.dev/badge/skills/bjorn-ingmanson/thefroject-plugins/maker-checker/github.svg)](https://agentmods.dev/skills/bjorn-ingmanson/thefroject-plugins/maker-checker)
Your own site
<a href="https://agentmods.dev/skills/bjorn-ingmanson/thefroject-plugins/maker-checker"><img src="https://agentmods.dev/badge/skills/bjorn-ingmanson/thefroject-plugins/maker-checker/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.

agentmods 80×15 button for maker-checker

Your own site · 80×15
<a href="https://agentmods.dev/skills/bjorn-ingmanson/thefroject-plugins/maker-checker"><img src="https://agentmods.dev/badge/skills/bjorn-ingmanson/thefroject-plugins/maker-checker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 608 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 $0.00046 $0.00608
Opus 5 $0.00023 $0.00304
Sonnet 5 $0.00009 $0.00122
Haiku 4.5 $0.00005 $0.00061

Measured 8d ago against content hash 91c63a00f2d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

maker-checker 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 8d 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.

customer-success/skills/maker-checker/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Maker-Checker

Separate creation from validation. One agent builds, another checks. They loop until the output passes.

When to Use This Pattern

  • Output quality matters and self-review is not enough
  • You have clear acceptance criteria that can be checked independently
  • The creator should focus on building, not second-guessing

Process

Phase 1: Define Acceptance Criteria

Before any work starts, write down what "done" looks like:

  • What must the output contain?
  • What must it NOT contain?
  • What quality bar must it meet? (compiles, passes tests, follows conventions, reads clearly)
  • Maximum iterations before escalating to the user (default: 3)

Phase 2: Make

Spawn the Maker agent with:

  • The full task description
  • All relevant context
  • The acceptance criteria (so it knows what the Checker will look for)
  • Write and edit tools as needed

The Maker produces the first version.

Phase 3: Check

Spawn the Checker agent with:

  • The Maker's output
  • The acceptance criteria
  • Read-only tools (the Checker never modifies the output directly)

The Checker returns one of:

  • PASS: Output meets all criteria. Include a brief summary of what was verified.
  • FAIL: Output does not meet criteria. List specific issues with line references.

Phase 4: Loop or Deliver

If PASS: deliver the output. Done.

If FAIL: send the Checker's feedback back to the Maker as a new agent call. The Maker revises and resubmits. Repeat until PASS or max iterations.

If max iterations reached: present both the latest output and the remaining issues to the user for a decision.

Example

Task: "Write a database migration to add user preferences"

Round 1:

  • Maker writes the migration
  • Checker reviews: "FAIL. Missing rollback function. No index on user_id foreign key."

Round 2:

  • Maker revises with Checker's feedback
  • Checker reviews: "PASS. Migration includes up/down, indexes, and matches existing naming conventions."

Rules

  • The Checker never edits the output. It only judges.
  • The Maker receives the Checker's full feedback, not a summary. Specifics drive better revisions.
  • Cap at 3 iterations. If 3 rounds of feedback cannot fix it, the task needs rethinking, not more loops.
  • Keep the Checker's tool set minimal. Read and Grep only. Independence is the point.
  • The acceptance criteria must be written before the first Make. Do not add new criteria mid-loop.

Read the full file on GitHub · 80 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. 8d ago First seen · 80 lines · 46 tokens per session scan A 91c63a00f2d2

Subscribe to this mod's changes

maker-checker is a skill published in the GitHub repository bjorn-ingmanson/thefroject-plugins (1 stars, last pushed 2mo ago), licensed MIT. It adds 46 tokens to every session and 608 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.