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.
npx agentmods add agents/kitchen-engineer42/joharnessburg/code-quality-reviewergit clone --depth 1 https://github.com/kitchen-engineer42/joharnessburgWrote 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.
[](https://agentmods.dev/agents/kitchen-engineer42/joharnessburg/code-quality-reviewer)<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>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 | $0.00087 | $0.00850 |
| Opus 5 | $0.00044 | $0.00425 |
| Sonnet 5 | $0.00017 | $0.00170 |
| Haiku 4.5 | $0.00009 | $0.00085 |
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.
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.
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.
- 5d ago First seen · 58 lines · 87 tokens per session scan A 6388b94af0ee
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.
Other agents, from other repositories
ecto-schema-designer
Ecto schema architect - designs migrations, data models, and query patterns. Use proactively when planning database structure for new features.
demand-generation
Demand Generation (CMO). Owns plugins/demand-generation/ and nothing else. Delegate work in this department's remit here.
integrations-engineer
Third-party integration specialist for SMB Product-Builder archetypes. Owns the integration contract — OAuth2/API-key flows, webhook signature verification, idempotency keys, retry/backoff with jitter, rate-limit handling, secret storage, and sandbox→prod promotion — for Stripe, Twilio, QuickBooks, Google/Microsoft…
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
ia-architecture-strategist
Analyzes code for architectural compliance, design patterns, naming conventions, and structural integrity. Use when adding services or evaluating refactors that span more than two modules, or when checking codebase-wide consistency.
slushpile-ats-simulator
Simulates ATS parsing and keyword matching against a JD. Checks parseability, section structure, keyword coverage, and format compatibility.