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 it235/multica-best-practices --skill multica-review-architectgit clone --depth 1 https://github.com/it235/multica-best-practicesWrote 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/it235/multica-best-practices/multica-review-architect)<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.
<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>- NVIDIA SkillSpector pass
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 | $0.00049 | $0.00412 |
| Opus 5 | $0.00024 | $0.00206 |
| Sonnet 5 | $0.00010 | $0.00082 |
| Haiku 4.5 | $0.00005 | $0.00041 |
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.
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)
- Soundness: layering, module boundaries, dependency direction clear; no over/under-design.
- Extensibility & maintainability: cost of common future changes; obvious tech debt.
- Acceptance alignment: line-by-line coverage of AC-/FR-/BR-; list gaps.
- Key technical risk: performance, consistency, security, data boundaries identified with mitigations; unmitigated risk = blocking.
- 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.
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.
- today Changed 0fc7f885fb4c
- 11d ago First seen · 38 lines · 49 tokens per session scan A f55407863b26
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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…