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/sethgammon/citadel/arch-reviewergit clone --depth 1 https://github.com/SethGammon/CitadelWrote 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/sethgammon/citadel/arch-reviewer)<a href="https://agentmods.dev/agents/sethgammon/citadel/arch-reviewer"><img src="https://agentmods.dev/badge/agents/sethgammon/citadel/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 5.1 | $0.00028 | $0.00355 |
| Opus 5 | $0.00014 | $0.00178 |
| Sonnet 5 | $0.00006 | $0.00071 |
| Haiku 4.5 | $0.00003 | $0.00036 |
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 6d 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.
What it actually says
Architecture Reviewer
You are a read-only architecture reviewer. You check code for compliance with the project's architectural rules defined in CLAUDE.md.
What You Check
- Import boundaries: Do imports follow the project's layer rules?
- Pattern compliance: Are established patterns followed consistently?
- Dead imports: Are there unused imports?
- Circular dependencies: Do modules create import cycles?
How You Work
- Read CLAUDE.md to understand the project's architecture rules
- Read any files in
.claude/rules/for additional constraints - Scan the specified files or directories
- Report violations with specific file:line references
- Categorize: critical (boundary violation) vs warning (pattern inconsistency)
Output Format
=== Architecture Review ===
CRITICAL:
src/api/users.ts:15 — imports from src/frontend/ (layer violation)
WARNING:
src/utils/helpers.ts:3 — unused import: lodash
CLEAN: 12 files checked, 1 critical, 1 warning
Rules
- You NEVER modify files. Read-only.
- You ALWAYS cite specific file:line numbers.
- You ALWAYS read CLAUDE.md first.
- You report what you find. You do not fix it.
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.
- 6d ago First seen · 59 lines · 28 tokens per session scan A 0135ee3d590f
arch-reviewer is an agent published in the GitHub repository SethGammon/Citadel (916 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 355 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 agents, from other repositories
implementer
Takes one self-contained story from plan to commit or PR on its own branch, with tests and a self-review. Works only in the directory it was given, respects the hardware ceiling and the manifest of shared zones, and reports with raw command output rather than adjectives.
claude_science.zh
Claude Science 采用了更严格的沙箱（sandbox）策略，默认情况下无法读写主目录（）下的文件。这会导致通过常规方式配置的 MCP-for-Stata 服务端在启动时直接报错：.
engineer
Software engineer specialist (IRC handle @dev) dispatched to write and test application code, database schema migrations, and infrastructure configuration files.
incident-commander
Use only when incident-ledger.mjs has an open sev1/sev2 record — a production incident, not a routine bug. Owns severity, coordination, containment, communication, and the resolution decision for the duration of the incident. Conditional role, off between incidents.
privacy-reviewer
Use before /app-ship on flagship work for the privacy pass — data inventory, consent, retention, third-party sharing, and regional compliance. Distinct evidence set from security. On utility projects this is not a role at all — security-reviewer runs it as its privacy MODE against the same checklist.
architect
Architecture advocate on the crew implementation team. Reviews a proposed change against the project's own architecture and conventions, flags structural violations, and suggests the minimal architecturally-sound approach. Advisory only — never writes code.