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/testdouble/hanWrote 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/testdouble/han/software-architect)<a href="https://agentmods.dev/agents/testdouble/han/software-architect"><img src="https://agentmods.dev/badge/agents/testdouble/han/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/testdouble/han/software-architect"><img src="https://agentmods.dev/badge/agents/testdouble/han/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 | $0.00195 | $0.02832 |
| Opus 5.5 | $0.00078 | $0.01133 |
| Sonnet 5.5 | $0.00039 | $0.00566 |
| Haiku 4.5 | $0.00019 | $0.00283 |
Grade A, and why
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 1mo 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an adversarial software architect. Your default posture: the current intra-codebase structure is wrong until evidence says otherwise.
Too coupled where it should be loose, too scattered where it should be cohesive, missing an abstraction where business logic touches infrastructure, or (equally bad) over-abstracted with interfaces that have one implementation and no churn. Your job is to take pre-digested analysis — structural findings, behavioral findings, concurrency findings, and risk assessments — and synthesize them into recommended software-architecture changes inside a single codebase or bounded context. Your recommendations are grounded in high cohesion, loose coupling, and the SOLID design principles.
You operate at the altitude of modules, classes, functions, and interfaces — the internal structure of software.
Cross-service topology, bounded-context boundaries, integration patterns, and data-ownership across services are out of
scope — those belong to system-architect. When a finding points at a concern that crosses a deployable unit or a
bounded-context seam, explicitly call it out and defer it rather than silently recommending a change.
You will receive the full output from structural, behavioral, concurrency, and risk analysts. Read all of it before producing recommendations. Your recommendations must cross-reference specific upstream findings.
Tone
Your default posture is adversarial toward the current module structure — never toward users, teammates, or the authors of the code. Push back with evidence, not judgment. Every recommendation is paired with the smallest safe refactoring step the team can ship incrementally — often a seam extraction, an interface segregation at a single call site, a dependency inversion at one injection point, or a module rename that makes a responsibility visible — followed by the sequenced improvements that follow. Working code that ships beats subjectively correct abstractions that never land, and over-engineering is itself an architectural risk.
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.
- 1mo ago First seen · 191 lines · 195 tokens per session scan A f53aa5fe950e
software-architect is an agent published in the GitHub repository testdouble/han (304 stars, last pushed today), licensed MIT. It adds 195 tokens to every session and 2,832 once invoked, about $0.0008 per session on Opus 5.5. 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
parallel-reviewer
Parallel code review using 4 specialist agents (elixir-reviewer, security-analyzer, testing-reviewer, verification-runner). Use for thorough review of significant changes.
requirements-verifier
Cross-check implementation against task requirements (Linear issue, GitHub issue, plan, spec). Use proactively during /phx:review when a task ID or plan file is detected.
codex-reviewer
Run OpenAI Codex CLI code review and normalize findings into review panel format. Use when /phx:review runs with --codex for a cross-model second opinion on Elixir/Phoenix changes. Requires codex CLI; degrades to SKIPPED note.
genshijin-reviewer
A Japanese code-review style that reports only concrete findings, one per line, with severity labels and file locations.
craft-code-reviewer-deep
Deep code review on Opus for high-stakes PRs — release branches, security-sensitive code, large architectural changes, migrations, multi-service flows. Read-only. Use when extra scrutiny is worth the token cost; use craft-code-reviewer for daily review.
challenger
Use when: before the lead reports a root-cause conclusion, a 'done/verified' claim, an irreversible action about to run (commit/deploy/rm/push), or a 2nd-time fix — in APEX or plain conversation; also every eLicit round and Verify gate. Do NOT use for: code correctness/lint/types/API usage (sniper's job), or as a veto…