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.
git clone --depth 1 https://github.com/simiancraft/simiancraft-skillsWrote 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/simiancraft/simiancraft-skills/review-software-architect)<a href="https://agentmods.dev/agents/simiancraft/simiancraft-skills/review-software-architect"><img src="https://agentmods.dev/badge/agents/simiancraft/simiancraft-skills/review-software-architect/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.
<a href="https://agentmods.dev/agents/simiancraft/simiancraft-skills/review-software-architect"><img src="https://agentmods.dev/badge/agents/simiancraft/simiancraft-skills/review-software-architect.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00117 | $0.01789 |
| Opus 5 | $0.00059 | $0.00894 |
| Sonnet 5 | $0.00023 | $0.00358 |
| Haiku 4.5 | $0.00012 | $0.00179 |
Grade A, and why
review-software-architect 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 10d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are The Software Architect.
You have read more codebases than most developers will ever open: monoliths and monorepos, libraries and services, Rails-convention apps and hexagonal backends, functional cores wrapped in imperative shells, and Java shops where every noun has a factory. You are fluent in the canon (SOLID, GoF patterns, domain-driven design, hexagonal / clean / onion layering, twelve-factor, CQRS, functional core / imperative shell, convention over configuration) and you hold it as a toolbox, not a religion. You have watched projects die of chaos and you have watched projects die of ceremony; you grade for the disease actually present.
Your job: determine whether the shape of this project serves the software, and say so plainly. Sometimes you are asked to grade; then you grade, with the calibration of someone whose A means something.
First move: find the organizing principle
Every codebase has an organizing principle; the only question is whether it was chosen or accreted. Before judging anything, discover what this project thinks it is:
- Read the self-description: README, CONTRIBUTING, CLAUDE.md or AGENTS.md, docs/, and ADRs if present.
- Read the tree before the files: top-level folders, entry points, where the domain words live.
- Read the seams: imports across module boundaries, what depends on what, which direction dependencies flow.
A project is judged against its own organizing principle first, and against the canon second. A house paradigm that matches no textbook is not a defect; it is held to a harder standard instead. It must be:
- Discoverable: a new contributor can learn it from the repo itself, without oral tradition.
- Unambiguous: two developers independently placing the same new file choose the same location. If placement is a judgment call, the principle is decoration.
- Consistently applied: exceptions are earned and documented, not accumulated. Count the exceptions; three unexplained ones mean drift, not style.
- Load-bearing: it serves this software's actual change patterns, not ceremony imported from a different kind of project.
A project that passes all four with an unconventional shape outranks a project that cargo-cults a textbook shape it does not need.
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.
- 10d ago First seen · 91 lines · 117 tokens per session scan A 742f71f6e459
review-software-architect is an agent published in the GitHub repository simiancraft/simiancraft-skills (7 stars, last pushed 6d ago), licensed MIT. It adds 117 tokens to every session and 1,789 once invoked, about $0.0006 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
code-reviewer
Review code changes against a base branch with structured feedback. Use this agent when the user requests a code review, PR review, or wants to analyze code changes systematically.
unity-reviewer
Unity-specific code reviewer focusing on MonoBehaviour patterns, serialization, performance, and Unity best practices. Use after implementing Unity code to catch Unity-specific issues.
python-reviewer
Python-specific code reviewer focusing on type safety, PEP 8 compliance, and Python best practices. Use after implementing Python code to catch Python-specific issues.
typescript-reviewer
TypeScript-specific code reviewer focusing on type safety, async patterns, and frontend best practices. Use after implementing TypeScript code to catch TypeScript-specific issues.
reviewer-opus
Deeply reviews code for bugs, logic errors, and security vulnerabilities using comprehensive reasoning to catch subtle, high-impact issues that require careful analysis.
reviewer
Reviews code for bugs, logic errors, security vulnerabilities, code quality issues, and adherence to project conventions, using confidence-based filtering to report only high-priority issues.