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)<a href="https://agentmods.dev/commands/davistroy/claude-marketplace/arch-synthesize"><img src="https://agentmods.dev/badge/commands/davistroy/claude-marketplace/arch-synthesize/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"><img src="https://agentmods.dev/badge/commands/davistroy/claude-marketplace/arch-synthesize.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 | $0.00025 | $0.00499 |
| Opus 5 | $0.00013 | $0.00249 |
| Sonnet 5 | $0.00005 | $0.00100 |
| Haiku 4.5 | $0.00003 | $0.00050 |
Grade A, and why
arch-synthesize 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 — Synthesize
Re-run synthesis from existing findings. Use after manually editing domain findings, re-running a single agent with /arch-review-single, or resolving cross-domain conflicts offline.
Usage: /arch-synthesize <path-to-target>
Parse target path from: $ARGUMENTS
-
Validate
<target-path>/arch-review/findings/exists — if not, stop and suggest running/arch-reviewfirst -
Discover and merge per-agent coverage meta:
ls <target-path>/arch-review/findings/*.meta.json 2>/dev/null || echo "No *.meta.json files found — agent meta unavailable"
Read each <agent-name>.meta.json file found and merge their entries into a single coverage map keyed by agent name. Only a subset of the standard 9 agents may have run — an agent missing its .meta.json file is not an error; treat it the same as a missing findings file (flag as "Domain not reviewed" per step 4).
- List all findings files present:
ls <target-path>/arch-review/findings/*.md 2>/dev/null
-
Note any agents from the standard 9 whose findings file is missing — flag in report header as "Domain not reviewed"
-
Read all present findings files
-
Run cross-domain conflict detection:
- Identify any finding in one domain that contradicts or creates tension with a finding in another
- Resolve using business impact as tiebreaker
- Document any unresolved conflicts in the executive summary
-
Produce fresh
<target-path>/arch-review/reports/executive-summary.md— overwrite existing- Begin with the Review Coverage table rendered from the merged per-agent meta (step 2)
- Follow the full report structure from
/arch-review
-
Print terminal summary:
- Total findings by severity across all available domains
- Any domains with Low/Medium confidence flagged for follow-up
- Path to executive summary
Do not re-run any domain agents. Synthesize from what exists.
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 · 50 lines · 25 tokens per session scan A 24fc67bc7118
arch-synthesize is a command published in the GitHub repository davistroy/claude-marketplace (5 stars, last pushed 4d ago), licensed MIT. It adds 25 tokens to every session and 499 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.