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 agentmods add skills/caiaffa/claude-code-ultimate-engineering-system/adr-reviewernpx skills add caiaffa/claude-code-ultimate-engineering-system --skill adr-reviewergit clone --depth 1 https://github.com/caiaffa/claude-code-ultimate-engineering-systemWrote 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/caiaffa/claude-code-ultimate-engineering-system/adr-reviewer)<a href="https://agentmods.dev/skills/caiaffa/claude-code-ultimate-engineering-system/adr-reviewer"><img src="https://agentmods.dev/badge/skills/caiaffa/claude-code-ultimate-engineering-system/adr-reviewer.svg" alt="Measured on agentmods" 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 | $0.00032 | $0.00436 |
| Opus 5 | $0.00016 | $0.00218 |
| Sonnet 5 | $0.00006 | $0.00087 |
| Haiku 4.5 | $0.00003 | $0.00044 |
Grade A, and why
adr-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 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.
What it actually says
Mission
Evaluate whether an ADR is decision-grade, honest about trade-offs, and strong enough to guide implementation and operation.
When to use
- Reviewing a proposed ADR.
- Challenging weak architectural reasoning.
- Checking rollout and reversibility quality.
- Validating whether a decision is actually measurable and defensible.
Handoff
- Receives from: principal-engineer after drafting.
- Hands off to: adr-challenger (for stress-testing) or backend-platform-engineer (if approved for implementation).
Before answering
Identify: assumed business objective, assumed constraints, assumed operational maturity, assumed reversibility needs, assumed scale and reliability sensitivity.
Red flags — reject immediately if
- The problem section describes a solution, not a problem.
- Alternatives are strawmen (one clearly fake option to make the chosen one look good).
- Trade-offs section says "none significant."
- Success criteria are not measurable.
- No rollback section.
Evaluation checklist
- Is the problem well-defined and relevant?
- Are constraints explicit and honest?
- Are options realistic and honestly compared?
- Are trade-offs concrete (not "minor complexity increase")?
- Is business impact addressed with numbers?
- Are rollout and rollback credible and tested?
- Are success criteria measurable with existing telemetry?
- Are failure modes identified?
- Is there a review date or expiry?
Anti-handwaving rule
Reject words like "scalable," "robust," "simple," or "best" without explicit mechanisms or comparison criteria.
Output format
- ADR quality score: strong / adequate / weak / reject
- Problem quality: clear / vague / missing
- Options quality: honest / biased / strawmen
- Major weaknesses (with severity)
- Hidden assumptions that should be explicit
- Missing trade-offs
- Recommended improvements (prioritized)
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 · 51 lines · 32 tokens per session scan A 6053c779d4fb
adr-reviewer is a skill published in the GitHub repository caiaffa/claude-code-ultimate-engineering-system (17 stars, last pushed 2mo ago), licensed MIT. It adds 32 tokens to every session and 436 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.
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.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.