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.
npx skills add mnzralee/claude-multi-agent-architecture --skill review-boardgit clone --depth 1 https://github.com/mnzralee/claude-multi-agent-architectureWrote 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/skills/mnzralee/claude-multi-agent-architecture/review-board)<a href="https://agentmods.dev/skills/mnzralee/claude-multi-agent-architecture/review-board"><img src="https://agentmods.dev/badge/skills/mnzralee/claude-multi-agent-architecture/review-board/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/skills/mnzralee/claude-multi-agent-architecture/review-board"><img src="https://agentmods.dev/badge/skills/mnzralee/claude-multi-agent-architecture/review-board.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 | $0.00092 | $0.00821 |
| Opus 5.5 | $0.00037 | $0.00328 |
| Sonnet 5.5 | $0.00018 | $0.00164 |
| Haiku 4.5 | $0.00009 | $0.00082 |
Grade A, and why
review-board 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 1mo 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Software Engineering Review Board (SERB)
A rigorous, multi-wave plan review. Gather verified ground truth, critique from five specialist lenses in parallel, then synthesize one refined plan with a go/no-go. Every reviewer is read-only; the board advises, it does not implement.
When to use
Invoke /review-board (or paste .claude/prompts/review-board.md after a plan in plan mode) when:
- The plan is high-stakes (touches auth, money, migrations, production, or a wide blast radius).
- The change is cross-cutting and a surface decision would miss ripples (pair with
.claude/rules/depth-first-impact-analysis.md). - You want an enterprise-grade refinement of a plan before committing to execution.
Skip it for one-sentence changes; the cost is not worth it there (see .claude/rules/ai-orchestration-decision-gate.md).
How to run
The full agent specifications live in .claude/prompts/review-board.md. Read that file and execute it against the current plan. In brief, it is three waves:
- Wave 1: Discovery (4 parallel, read-only) gathers ground truth, not critique:
- Codebase Deep Explorer (actual paths, selectors, endpoints versus the plan's assumptions)
- Best-Practices Researcher (current standards and pitfalls per technology, via WebSearch)
- Live-State Verifier (real, non-mutating checks of what is actually up)
- Dependency & Risk Mapper (dependency graph, failure modes, hidden assumptions, rollback)
- Wave 2: The Board (5 parallel specialists, read-only) critiques against the Wave 1 ground truth: Chief Architect, Testing & Reliability Lead, Security & Compliance Lead, DevOps & Infrastructure Lead, Quality & Standards Lead. Each returns CRITICAL/HIGH/MEDIUM/LOW findings with
file:lineevidence and the fix. - Wave 3: Synthesis deduplicates and ranks findings, resolves conflicts using ground truth, and delivers the aggregate findings table, the refined executable plan, a Go/No-Go (GREEN/YELLOW/RED), and a quality scorecard.
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.
- 1mo ago First seen · 47 lines · 92 tokens per session scan A 0f23506cf353
review-board is a skill published in the GitHub repository mnzralee/claude-multi-agent-architecture (8 stars, last pushed 26d ago), licensed MIT. It adds 92 tokens to every session and 821 once invoked, about $0.0004 per session on Opus 5.5. 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 skills, from other repositories
coordinate-review
Review a Coordinate Agents implementation as the Codex Reviewer. Verify the real commit, diff, tests, validation evidence, and specification without modifying the Implementer's product code.
feature-dev
A general workflow for developing a software feature, from exploring the existing project through planning, implementation, independent review, and final owner acceptance. It adapts the amount of work to the feature's size and risk.
tech-debt-audit
Audits architectural choices for hidden scalability bottlenecks and operational tech debt.
senior-review
A pre-merge review process that sends the same code change to two independent reviewers with different focuses, then combines their findings into one decision. One checks maintainability and change discipline; the other checks affected areas, edge cases, and regression risk.
verify-3way
A release-checking process that combines automated regression tests, a fresh reproduction test, and a review against the written requirements. The fresh reproduction test starts from the original user problem without giving the tester background about the fix.
reviewer-openaccp
Perform read-only OpenACCP sidecar review of a task card, branch, diff, handoff, prompt, or status artifact. Use to check scope compliance, correctness, verification evidence, side effects, overclaiming, and readiness for final-authority consume.