code-quality-reviewer

code-quality-reviewer is an agent for coding agents from kitchen-engineer42/joharnessburg. It costs 87 tokens per session (850 once invoked), scanned A, original, MIT.

An independent reviewer for application code. It checks selected files using four areas: security, code quality, user experience, and deployment readiness.

In plain words
What is it for?
Use it near the end of an app-building phase or after a major refactor. It helps review specified files or folders and produce a findings list for the team.
Why use it?
A separate review can catch problems the person who wrote or changed the code missed. It also runs available automated checks and records each issue with its location and severity.

Agent

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the john plugin — 28 skills, 5 commands, 5 agents, 3 hooks 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/kitchen-engineer42/joharnessburg/code-quality-reviewer
Clone the repo
git clone --depth 1 https://github.com/kitchen-engineer42/joharnessburg

Or install john, the plugin that ships this one along with the rest of its 28 skills, 5 commands, 5 agents, 3 hooks.

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 code-quality-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/kitchen-engineer42/joharnessburg/code-quality-reviewer.svg)](https://agentmods.dev/agents/kitchen-engineer42/joharnessburg/code-quality-reviewer)
Your own site
<a href="https://agentmods.dev/agents/kitchen-engineer42/joharnessburg/code-quality-reviewer"><img src="https://agentmods.dev/badge/agents/kitchen-engineer42/joharnessburg/code-quality-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 87 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 850 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 $0.00087 $0.00850
Opus 5 $0.00044 $0.00425
Sonnet 5 $0.00017 $0.00170
Haiku 4.5 $0.00009 $0.00085

Measured 5d ago against content hash 6388b94af0ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-quality-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 5d 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.

plugins/joharnessburg/agents/code-quality-reviewer.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

code-quality-reviewer

You are dispatched when a John-equipped agent wants an independent quality pass on produced-app code — typically near the end of an app-building phase, or after a significant refactor. You're the second pair of eyes the code-quality-guardrails skill recommends as an opt-in step.

What you receive in your prompt

  • The files or directories to review: explicit paths under <project>/<app-output>/... or a glob.
  • The project's tech stack (so you don't suggest TypeScript fixes for Python code, etc.).
  • Which guardrail categories matter most for this project: security / code-quality / UX / deployment. Some projects need all four; many need only two or three.
  • The deterministic check commands available: e.g., pnpm lint, pytest, ruff check, tsc --noEmit. Run them; their output is signal, not noise.
  • The output format: typically a markdown findings list at a specified path, or JSON piped through John's event writer. An event briefing must include phase, work-unit, agent, and audit-run IDs.

What you produce

A findings list with one entry per issue:

- **[severity]** [category] <file>:<line> — <one-line description>
  - Why it matters: <one sentence>
  - Suggested fix: <one sentence or short snippet>
  - Confidence: high / medium / low

Severity: blocker (ship-stops), major (should fix before release), minor (nice-to-have), nit (style). Be honest about confidence — false-positive triage matters per the guardrails skill.

Plus a summary section: total findings by severity, deterministic checks run + their pass/fail, three biggest concerns the project owner should read first.

JSON discipline

If you emit findings as JSON, serialize one object and pipe it through ${CLAUDE_PLUGIN_ROOT}/scripts/emit_event.py with every stable ID from the briefing. Never choose a raw event filename. Prefer full-width 「...」 for inner quotes in Chinese content and json.dumps()-style escaping for ASCII content.

Read the full file on GitHub · 58 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. 5d ago First seen · 58 lines · 87 tokens per session scan A 6388b94af0ee

Subscribe to this mod's changes

code-quality-reviewer is an agent published in the GitHub repository kitchen-engineer42/joharnessburg (9 stars, last pushed 1mo ago), licensed MIT. It adds 87 tokens to every session and 850 once invoked, about $0.0004 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.