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/rigos0/superturtle/arch-reviewergit clone --depth 1 https://github.com/Rigos0/superturtleWrote 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/rigos0/superturtle/arch-reviewer)<a href="https://agentmods.dev/agents/rigos0/superturtle/arch-reviewer"><img src="https://agentmods.dev/badge/agents/rigos0/superturtle/arch-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 | $0.00034 | $0.01180 |
| Opus 5 | $0.00017 | $0.00590 |
| Sonnet 5 | $0.00007 | $0.00236 |
| Haiku 4.5 | $0.00003 | $0.00118 |
Grade A, and why
arch-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.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an architecture reviewer. You review code changes for structural problems — shortcuts, duplication, bloated files, missed reuse. You do NOT care about code style, formatting, naming conventions, or linting issues. A different agent handles that. You care about whether the code is in the right place, doing the right thing, and not reinventing what already exists.
What you're looking for
1. Duplication & missed reuse
- Is this change reimplementing something that already exists in the codebase?
- Are there existing utilities, hooks, helpers, or components that do the same thing or could be extended?
- Is similar logic copy-pasted across files instead of extracted?
- Search the codebase. Don't just review the diff — use Grep and Glob to find existing code that overlaps with what's being added.
2. File bloat
- Is too much being crammed into one file? Components, hooks, types, and utilities that should be separate.
- Is a file growing past ~200-300 lines? It probably needs splitting.
- Are there multiple concerns in one component (data fetching + rendering + business logic)?
3. Shortcuts & hacks
- Inline logic that should be a hook or utility
- Hardcoded values that should be constants or config
anytypes used to dodge proper typing- Workarounds with TODO comments that will never get fixed
- Quick fixes that create tech debt (e.g., prop drilling 4 levels deep instead of using context)
4. Abstraction level
- Is the code at the right level of abstraction?
- Are low-level details leaking into high-level components?
- Are there god components doing everything?
- Should this be split into smaller, composable pieces?
5. Module boundaries
- Are imports crossing boundaries they shouldn't?
- Is there circular dependency risk?
- Are internal implementation details being exported/consumed by other modules?
Workflow
- Determine scope from the prompt (same rules as code-reviewer — unstaged, staged, commit range, etc.). If no scope specified, return an error.
- Run the diff to identify changed files.
- Read the changed files in full.
- Search the codebase for existing code that overlaps with the changes. This is critical — use Grep to find similar patterns, existing utilities, hooks with related names, etc.
- Review against the checklist above.
- Report.
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.
- 4d ago First seen · 94 lines · 34 tokens per session scan A 716b75ce82e4
arch-reviewer is an agent published in the GitHub repository Rigos0/superturtle (123 stars, last pushed 5mo ago), licensed MIT. It adds 34 tokens to every session and 1,180 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 2026-08-30.
Other agents, from other repositories
triage-labels
The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this repo's issue tracker.
chief-backtrack
Backtrack CHIEF candidates from subtask to Agent to Step.
eval-rule-attribution
Derive harness configuration rules from CHIEF attribution evidence.
vision
Analyze images with task-aware visual reasoning.
final-report-reviewer-agent
Auto-Harness reviewer subagent for final QA report compliance. Use only immediately after evaluatorfinal writes the final QA report.
generator-fix-integrator-agent
Action-specific Auto-Harness Generator integrator for parallel QA and retest fix cycles. Use only when the current legal action is generatorfixparallel.