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 kumaran-is/claude-code-onboarding --skill architect-reviewgit clone --depth 1 https://github.com/kumaran-is/claude-code-onboardingWrote 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/kumaran-is/claude-code-onboarding/architect-review)<a href="https://agentmods.dev/skills/kumaran-is/claude-code-onboarding/architect-review"><img src="https://agentmods.dev/badge/skills/kumaran-is/claude-code-onboarding/architect-review/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/kumaran-is/claude-code-onboarding/architect-review"><img src="https://agentmods.dev/badge/skills/kumaran-is/claude-code-onboarding/architect-review.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 | $0.00047 | $0.01412 |
| Opus 5 | $0.00023 | $0.00706 |
| Sonnet 5 | $0.00009 | $0.00282 |
| Haiku 4.5 | $0.00005 | $0.00141 |
Grade A, and why
architect-review 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 6d 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Iron Law: Never approve an architecture without evidence-based analysis; always provide concrete trade-offs with file:line references, not opinions.
Architect Review Skill
Elite architectural review specialist. Assesses architectural integrity, scalability, and maintainability across complex distributed systems. Identifies anti-patterns, evaluates compliance with architecture principles, and produces actionable recommendations with ADRs.
Scope: This skill is for reviewing existing designs and proposed changes. For designing new architecture, use architecture-design. For full DDD analysis, use ddd-architect. For 5-phase plan review, use plan-mode-review.
When to Use
- Reviewing system architecture or major design changes before implementation
- Evaluating scalability, resilience, or maintainability impact of a proposed change
- Assessing architecture compliance with Clean Architecture / Hexagonal / DDD / microservices principles
- Identifying architectural anti-patterns in existing code or design docs
- Reviewing distributed system design (Saga, Outbox, CQRS, event sourcing)
When NOT to Use
- Small code review without architectural impact → use
code-reviewer - Designing new architecture from scratch → use
architecture-design - 5-phase plan gate review → use
plan-mode-review
Review Process
- Gather context — Identify system goals, constraints, and current state
- Assess impact — Rate each concern: HIGH / MEDIUM / LOW
- Evaluate compliance — Check against SOLID, DDD, Clean Architecture, or distributed patterns as applicable
- Identify violations — Anti-patterns, missing resilience, security gaps, data architecture issues
- Recommend improvements — Specific refactoring suggestions with concrete next steps
- Document — Produce ADR for irreversible or significant decisions (delegate to
architecture-decision-records)
Output Format
## Architecture Review: [System/Feature Name]
### Context
[System goals, constraints, current state]
### Impact Assessment
| Area | Rating | Evidence |
|------|--------|----------|
| [concern] | HIGH/MEDIUM/LOW | [file:line or design element] |
### Pattern Compliance
✅ [What is correct]
❌ [Violations with specific evidence]
### Anti-Patterns Detected
- [Pattern name]: [Description] — [Concrete fix]
### Recommendations
1. [Specific action with implementation guidance]
### ADRs Required
- ADR-XXXX: [Title] — [Decision to document]
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.
- 6d ago First seen · 149 lines · 47 tokens per session scan A 30c13bae5881
architect-review is a skill published in the GitHub repository kumaran-is/claude-code-onboarding (35 stars, last pushed 2mo ago), licensed MIT. It adds 47 tokens to every session and 1,412 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 2026-09-03.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
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.
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…