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.eval)<a href="https://agentmods.dev/commands/davistroy/claude-marketplace/arch-review-single.eval"><img src="https://agentmods.dev/badge/commands/davistroy/claude-marketplace/arch-review-single.eval/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.eval"><img src="https://agentmods.dev/badge/commands/davistroy/claude-marketplace/arch-review-single.eval.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 | $0.00000 | $0.00460 |
| Opus 5 | $0.00000 | $0.00230 |
| Sonnet 5 | $0.00000 | $0.00092 |
| Haiku 4.5 | $0.00000 | $0.00046 |
Grade A, and why
arch-review-single.eval 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
Eval: /arch-review-single
Purpose
Runs one domain agent from the architecture review team against a target codebase, without running the full 9-agent /arch-review suite. Good output: a single findings/<agent-name>.md (plus its .meta.json) written for the requested domain, using an existing intake.md when present, without touching any other domain's findings.
Fixtures
None — operates on an arbitrary target codebase path; can be run against this repository itself.
Test Scenarios
S1: Happy path — single domain against this repo
Invocation: /arch-review-single security-architect .
Must:
- Validates
security-architectagainst the documented list of 9 valid agent names - Reuses
<target-path>/arch-review/intake.mdif it exists, rather than re-running intake - Ensures
<target-path>/arch-review/findings/exists before dispatch - Dispatches via the Agent tool with
subagent_type: "personal-plugin:security-architect" - Writes
<target-path>/arch-review/findings/security-architect.mdandsecurity-architect.meta.json - Prints a findings summary to the terminal on completion
- Does not modify or delete any other agent's existing findings file
Must NOT:
- Dispatch any agent other than the one requested
- Fabricate findings if the target has no obvious issues in that domain
S2: Invalid agent name
Invocation: /arch-review-single not-a-real-agent .
Must:
- Detects the name is not one of the 9 valid domain agents
- Prints the valid agent-name list
- Stops before dispatching any agent
Rubric
| Criterion | Pass Threshold |
|---|---|
| Only the requested domain agent is dispatched | Required |
| Existing intake.md is reused, not regenerated | Required |
| Findings + meta files are written per the documented naming convention | Required |
| Invalid agent name is rejected before dispatch | Required |
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 · 55 lines · 0 tokens per session scan A 0c6eeede5b14
arch-review-single.eval is a command published in the GitHub repository davistroy/claude-marketplace (5 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 460 tokens. 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.