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/davistroy/claude-marketplaceWrote 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/commands/davistroy/claude-marketplace/arch-review-single)<a href="https://agentmods.dev/commands/davistroy/claude-marketplace/arch-review-single"><img src="https://agentmods.dev/badge/commands/davistroy/claude-marketplace/arch-review-single/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/commands/davistroy/claude-marketplace/arch-review-single"><img src="https://agentmods.dev/badge/commands/davistroy/claude-marketplace/arch-review-single.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 | $0.00015 | $0.00562 |
| Opus 5 | $0.00008 | $0.00281 |
| Sonnet 5 | $0.00003 | $0.00112 |
| Haiku 4.5 | $0.00002 | $0.00056 |
Grade A, and why
arch-review-single 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 11d 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 Review — Single Domain Agent
Run one domain reviewer against a target. Use for re-running after remediation, targeted spot-checks, or adding a domain to an existing review.
Usage: /arch-review-single <agent-name> <path-to-target>
Valid agent names:
solutions-architect— Architecture fit, patterns, NFRsdata-architect— Data models, storage, governanceintegration-architect— APIs, contracts, events, resiliencesoftware-engineer— Code quality, design, technical debtperformance-engineer— Scalability, structural performance risksqa-architect— Test strategy, coverage, CI gatessecurity-architect— Threat model, SAST, AppSec, dependenciesplatform-engineer— CI/CD, IaC, observability, ops readinessrisk-compliance— Regulatory, audit trail, business continuity
Parse from: $ARGUMENTS
Format: <agent-name> <target-path>
- Extract agent name (first token) and target path (remainder)
- Validate agent name against the list above — if invalid, print valid names and stop
- Check if
<target-path>/arch-review/intake.mdexists:- If yes: use it as the intake context
- If no: perform a brief intake pass (5-minute reconnaissance: stack detection, README read, directory structure)
- Ensure output directory exists:
mkdir -p <target-path>/arch-review/findings - Dispatch via the Agent tool with
subagent_type: "personal-plugin:<agent-name>"(fall back to the bare<agent-name>if the namespaced subagent type does not resolve). Pass only the intake context, target path, and output paths — do NOT read or inline the agent's definition file; the registered agent supplies its own system prompt. - Agent writes findings to
<target-path>/arch-review/findings/<agent-name>.md - Agent writes its own
<target-path>/arch-review/findings/<agent-name>.meta.json(per-agent file, not a shared/merged meta file) - Print findings summary to terminal on completion
If this is a re-run (findings file already exists), the new output overwrites the previous. Run /arch-synthesize <target-path> afterward to regenerate the executive summary.
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.
- 11d ago First seen · 43 lines · 15 tokens per session scan A db92dda74475
arch-review-single is a command published in the GitHub repository davistroy/claude-marketplace (5 stars, last pushed 4d ago), licensed MIT. It adds 15 tokens to every session and 562 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
argos
A command for checking whether an implementation matches its design deliverables. Its Korean description compares the work to the design as part of a completion inspection.