Borrowing it
Nothing to install: this file belongs to stefanhoelzl/codehydra. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/stefanhoelzl/codehydra/main/.claude/commands/review-quality.mdgit clone --depth 1 https://github.com/stefanhoelzl/codehydraWrote 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/commands/stefanhoelzl/codehydra/review-quality)<a href="https://agentmods.dev/commands/stefanhoelzl/codehydra/review-quality"><img src="https://agentmods.dev/badge/commands/stefanhoelzl/codehydra/review-quality.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 5.1 | $0.00010 | $0.02189 |
| Opus 5 | $0.00005 | $0.01094 |
| Sonnet 5 | $0.00002 | $0.00438 |
| Haiku 4.5 | $0.00001 | $0.00219 |
Grade A, and why
review-quality 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.
How it starts
The opening of the file, as written. The whole thing — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are orchestrating a quality review of the CodeHydra codebase.
Available Topics
| Topic | Description |
|---|---|
| architecture | Layer violations, circular deps, boundary violations, god modules |
| code-quality | Duplication, complexity, dead code, scattered responsibilities |
| consistency | Pattern deviations, naming, error handling, async patterns |
| documentation | Completeness, accuracy, AI-readability, structure |
| type-safety | tsconfig strictness, API type design, type-driven correctness |
| testing | TESTING.md enforcement, test type compliance, behavioral mocks |
| infrastructure | Dependencies, project layout, tooling, CI/CD, scripts |
| ux | Accessibility, UI patterns, user flows, keyboard navigation |
Parse User Intent
$ARGUMENTS
Interpret naturally:
- Empty or "all": run all 8 topics
- "only X and Y" or "focus on X": whitelist those topics
- "skip X" or "except X": blacklist those topics
- "help", "?", or "what topics": show the topics table above and exit
- Any other text: interpret the intent naturally
Execution
Launch Plan agents in parallel for each selected topic using the prompts below.
Each agent invocation MUST:
- Read docs/QUALITY.md first (their topic section + Accepted Patterns)
- Read the reference docs listed for that topic
- Explore the ENTIRE codebase systematically
- Use WebFetch for online research when uncertain about best practices
- Filter out issues matching "Accepted Patterns" in docs/QUALITY.md
- Focus on CODEBASE-WIDE patterns, not localized issues
- Assess severity (Critical or Warning) based on impact and spread
- Return max 10 issues
Topic Prompts
architecture
Review CodeHydra for ARCHITECTURE quality issues.
Read first:
- docs/QUALITY.md (Architecture section + Accepted Patterns)
- docs/ARCHITECTURE.md
- docs/INTENTS.md
- docs/AGENTS.md
- CLAUDE.md (External System Access Rules, Path Handling)
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.
- 8d ago First seen · 309 lines · 10 tokens per session scan A 0aebbee3c018
review-quality is a command published in the GitHub repository stefanhoelzl/codehydra (20 stars, last pushed 10d ago), licensed MIT. It adds 10 tokens to every session and 2,189 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
branch-review
Review a branch before merge [target] [level].
delegate-review
Run OCR in delegation mode — OCR handles file selection and rules, the host agent performs the actual review.
plannotator-review
Open interactive code review for current changes or a PR URL.
review.v1
Review code changes: /review [commit|branch|PR].
arch-suggest
Sugerir mejoras de arquitectura basadas en detección previa.
root-cause
Use when any test fails, bug appears, or behaviour surprises you, before proposing a fix - find the cause and prove it, by reading real evidence, tracing bad values back to their origin, comparing against a working case, and testing one hypothesis at a time.