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-synthesize.eval)<a href="https://agentmods.dev/commands/davistroy/claude-marketplace/arch-synthesize.eval"><img src="https://agentmods.dev/badge/commands/davistroy/claude-marketplace/arch-synthesize.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-synthesize.eval"><img src="https://agentmods.dev/badge/commands/davistroy/claude-marketplace/arch-synthesize.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 | $0.00499 |
| Opus 5 | $0.00000 | $0.00249 |
| Sonnet 5 | $0.00000 | $0.00100 |
| Haiku 4.5 | $0.00000 | $0.00050 |
Grade A, and why
arch-synthesize.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.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Eval: /arch-synthesize
Purpose
Re-synthesizes the executive summary from existing domain findings, without re-running any domain agent. Used after manually editing findings, re-running a single agent via /arch-review-single, or resolving cross-domain conflicts offline. Good output: a fresh reports/executive-summary.md built only from findings files already on disk.
Fixtures
None — operates on an existing <target-path>/arch-review/findings/ directory; can be run against this repository itself after a prior /arch-review or /arch-review-single run.
Test Scenarios
S1: Happy path — re-synthesize from existing findings
Setup: <target-path>/arch-review/findings/ already contains at least one <agent-name>.md and <agent-name>.meta.json pair from a prior review run.
Invocation: /arch-synthesize .
Must:
- Validates
<target-path>/arch-review/findings/exists before proceeding - Merges per-agent
*.meta.jsoncoverage into a single coverage map - Treats an agent missing its
.meta.json/.mdpair as "Domain not reviewed", not an error - Reads all present findings files and runs cross-domain conflict detection
- Overwrites
<target-path>/arch-review/reports/executive-summary.mdwith a fresh report, including the Review Coverage table - Prints a terminal summary with total findings by severity and the path to the executive summary
Must NOT:
- Dispatch or re-run any domain agent
- Fabricate a finding for a domain with no findings file present
S2: Error — no findings directory
Setup: <target-path>/arch-review/findings/ does not exist.
Invocation: /arch-synthesize .
Must:
- Stops without attempting synthesis
- Suggests running
/arch-reviewfirst
Rubric
| Criterion | Pass Threshold |
|---|---|
| No domain agent is re-run | Required |
| Missing per-agent files are flagged as "Domain not reviewed", not fatal | Required |
| Executive summary is rebuilt from findings currently on disk | Required |
| Missing findings directory produces a clean, actionable error | 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 · 57 lines · 0 tokens per session scan A 0810bf1608c0
arch-synthesize.eval is a command published in the GitHub repository davistroy/claude-marketplace (5 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 499 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.