multica-review-architect

multica-review-architect is a skill for Claude Code, Codex from it235/multica-best-practices. It costs 49 tokens per session (412 once invoked), scanned A, original, MIT.

A dedicated review framework for checking a software architecture design. It evaluates structure, future maintainability, requirements coverage, technical risks, and consistency between system parts.

In plain words
What is it for?
It is for reviewing an architecture design, deciding PASS or FAIL, listing required fixes, and performing a follow-up review after changes.
Why use it?
It gives architecture reviews a consistent way to find blocking gaps and distinguish them from optional suggestions. It also checks the design against acceptance criteria and related artifacts.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for reviewing an architecture design, deciding PASS or FAIL, listing required fixes, and performing a follow-up review after changes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/it235/multica-best-practices/multica-review-architect
Install

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.

Any agent
npx skills add it235/multica-best-practices --skill multica-review-architect
Clone the repo
git clone --depth 1 https://github.com/it235/multica-best-practices

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for multica-review-architect

README.md
[![agentmods](https://agentmods.dev/badge/skills/it235/multica-best-practices/multica-review-architect/github.svg)](https://agentmods.dev/skills/it235/multica-best-practices/multica-review-architect)
Your own site
<a href="https://agentmods.dev/skills/it235/multica-best-practices/multica-review-architect"><img src="https://agentmods.dev/badge/skills/it235/multica-best-practices/multica-review-architect/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.

agentmods 80×15 button for multica-review-architect

Your own site · 80×15
<a href="https://agentmods.dev/skills/it235/multica-best-practices/multica-review-architect"><img src="https://agentmods.dev/badge/skills/it235/multica-best-practices/multica-review-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 412 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00049 $0.00412
Opus 5 $0.00024 $0.00206
Sonnet 5 $0.00010 $0.00082
Haiku 4.5 $0.00005 $0.00041

Measured today against content hash 0fc7f885fb4c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

multica-review-architect 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 today.

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.

templates/en_US/skills/reviewer/multica-review-architect/SKILL.md · 38 lines

What it actually says

Architecture Design Professional Review (ArchReviewer)

Structured professional review framework for technical architecture design artifacts. Called by ArchReviewer; reviews the design link Architect returns via multica-artifact-architect.

When to use

  • ArchReviewer receives a "review architecture design" dispatch from Leader.
  • Entering a re-review round after design changes (check previous round's fix list item by item).

Review dimensions (conclusion per item)

  1. Soundness: layering, module boundaries, dependency direction clear; no over/under-design.
  2. Extensibility & maintainability: cost of common future changes; obvious tech debt.
  3. Acceptance alignment: line-by-line coverage of AC-/FR-/BR-; list gaps.
  4. Key technical risk: performance, consistency, security, data boundaries identified with mitigations; unmitigated risk = blocking.
  5. Cross-end consistency: contract boundaries with frontend/backend self-consistent, no conflict with UI/API artifacts.

Output format

【Architecture Review】<design link>
Conclusion: PASS / FAIL
Blocking items (required on FAIL, each: rationale / involved point / fix direction):
- ...
Suggestions (non-blocking):
- ...
Previous fix-list check (re-review): resolved X / unresolved Y
Round: N / 3

Conclusion + fix list reported to Leader; don't modify design or notify Architect yourself.

Boundaries

  • Review only architecture design, not UI, requirements, code, or test cases.
  • Don't replace Leader's generic gate (multica-verification skill).
  • Still FAIL at round 3 → mark "escalate to human", hand to Leader, stop looping.
Changes

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.

  1. today Changed 0fc7f885fb4c
  2. 11d ago First seen · 38 lines · 49 tokens per session scan A f55407863b26

Subscribe to this mod's changes

multica-review-architect is a skill published in the GitHub repository it235/multica-best-practices (114 stars, last pushed yesterday), licensed MIT. It adds 49 tokens to every session and 412 once invoked, about $0.0002 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 2026-08-30.