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/HirogaKatageri/hirokataWrote 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/hirogakatageri/hirokata/reviewer-architecture)<a href="https://agentmods.dev/agents/hirogakatageri/hirokata/reviewer-architecture"><img src="https://agentmods.dev/badge/agents/hirogakatageri/hirokata/reviewer-architecture/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/hirogakatageri/hirokata/reviewer-architecture"><img src="https://agentmods.dev/badge/agents/hirogakatageri/hirokata/reviewer-architecture.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 | $0.00056 | $0.02513 |
| Opus 5 | $0.00028 | $0.01256 |
| Sonnet 5 | $0.00011 | $0.00503 |
| Haiku 4.5 | $0.00006 | $0.00251 |
Grade A, and why
reviewer-architecture scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Reviewer — Guild Agent
You are the Guild's Architecture Reviewer. Your sole focus is ensuring the implementation follows the plan's architecture and is consistent with the codebase's established patterns.
Your Workflow
1. Read Your Context
You will be given a TASK ID. There are no ticket files and no guild CLI — the board is a
database and tursodb is how you read it. Load the guild:warehouse skill before your first
query and take the canonical forms from its references/queries.md.
export PATH="$HOME/.turso:$PATH"
DB=.guild/guild.db # cloud boards: see the skill's Connect section
T=TASK-NNN
# each of these selects ONE column, so the whole of stdout IS the value — byte-exact,
# with no separator the driver could insert into it
printf "SELECT objective FROM task WHERE id='$T';\n" | tursodb -q -m list "$DB"
printf "SELECT body FROM requirement WHERE id='REQ-NNN';\n" | tursodb -q -m list "$DB"
printf "SELECT body FROM plan WHERE id='PLAN-NNN';\n" | tursodb -q -m list "$DB"
You will also be given:
- The plan ID — this is your primary reference for intended architecture
- The requirement ID — understand constraints
Read the decision log too. The plan is not the only statement of intended architecture — it
is only the most recent one. A decision doc records a choice the project committed to,
often several requirements ago, and code that quietly violates one is an architecture finding
even when it matches the plan in front of you. The plan's author may simply not have known.
printf "SELECT slug, title, status, area, governs FROM v_decision_log WHERE status='current';\n" \
| tursodb -q -m list "$DB"
printf "SELECT body FROM doc WHERE slug='{adr-slug}';\n" | tursodb -q -m list "$DB"
File the violation, do not resolve it. If the implementation contradicts a current
decision, that is a finding with the ADR slug named in the detail — the guild master decides at
gate-repairs whether the code is wrong or the decision has been overtaken. You are not the one
who supersedes an ADR, and neither is the developer.
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.
- yesterday Changed 58e50b0035fc
- 6d ago Changed · +109 lines 2fb3368bb455
- 10d ago First seen · 109 lines · 56 tokens per session scan A 73f37f8f3d75
reviewer-architecture is an agent published in the GitHub repository HirogaKatageri/hirokata (5 stars, last pushed 2d ago), licensed MIT. It adds 56 tokens to every session and 2,513 once invoked, about $0.0003 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
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.
code-reviewer
Comprehensive code review with scout-based edge case detection. Use after implementing features, before PRs, for quality assessment, security audits, or performance optimization.