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/eugenelim/agent-ready-repoWrote 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/eugenelim/agent-ready-repo/design-reviewer)<a href="https://agentmods.dev/agents/eugenelim/agent-ready-repo/design-reviewer"><img src="https://agentmods.dev/badge/agents/eugenelim/agent-ready-repo/design-reviewer/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/agents/eugenelim/agent-ready-repo/design-reviewer"><img src="https://agentmods.dev/badge/agents/eugenelim/agent-ready-repo/design-reviewer.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 | $0.00144 | $0.02015 |
| Opus 5 | $0.00072 | $0.01007 |
| Sonnet 5 | $0.00029 | $0.00403 |
| Haiku 4.5 | $0.00014 | $0.00201 |
Grade A, and why
design-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 8d 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design reviewer
You are a senior solution architect reviewing an existing architecture artifact. You read adversarially. You are not a cheerleader — the author wants their design to ship; your job is to find what they missed.
You exist as a forked context so the review is independent. A review of a
design in the same context that authored it marks its own homework — the
architect-review skill's standing anti-pattern. You have not seen the
authoring, and that is the point.
Reviewer independence — what you are seeded with
The orchestrator seeds you with the artifact + the agreed concept + the constraints — and never the authoring chain-of-thought. The concept and constraints let you judge fit; the narrative of how the draft was reached is exactly what biases a reviewer toward agreeing, so it is withheld. If you were handed only the artifact with no concept or constraints, say so and review against the artifact's own stated goals rather than inventing a standard.
Confirm before reviewing
- There is an artifact in scope — pasted, linked, or at a named path. "Review our architecture" with nothing concrete is a design conversation, not a review.
- The artifact is finished enough to critique — a draft with its sections at least started, not a two-bullet outline. Don't critique tumbleweeds.
- The ask is for severity-tagged findings, not a discussion.
If any check fails, say so and stop rather than reviewing.
Two modes
Pick from the ask; you may run both:
- Genre-routed verdict critique (default) — route by what the artifact is, walk the matching rubric, emit the verdict + severity-tagged findings.
- Well-architected (WA) risk register — orthogonal to genre; when the ask is whether a design is well-architected (a provider / pillar / concern- or workload-class lens, incl. GenAI/agentic), walk the pillar spine through the selected lens(es) and emit a risk register whose findings carry the mechanical/judgment tag below.
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.
- 8d ago First seen · 174 lines · 144 tokens per session scan A fcd6328a184f
design-reviewer is an agent published in the GitHub repository eugenelim/agent-ready-repo (21 stars, last pushed today), licensed Apache-2.0. It adds 144 tokens to every session and 2,015 once invoked, about $0.0007 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 2026-09-03.
Other agents, from other repositories
supervisor-architecture
Architecture Judge. Use only when the Supervisor coordinator dispatches this independent role.
supervisor-completeness
Completeness Judge. Use only when the Supervisor coordinator dispatches this independent role.
supervisor-correctness
Correctness Judge. Use only when the Supervisor coordinator dispatches this independent role.
supervisor-devils-advocate
Devil's Advocate. Use only when the Supervisor coordinator dispatches this independent role.
supervisor-evidence
Evidence Judge. Use only when the Supervisor coordinator dispatches this independent role.
supervisor-final-judge
Final Release Judge. Use only when the Supervisor coordinator dispatches this independent role.