Borrowing it
Nothing to install: this file belongs to Atypical-Consulting/AdrMcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Atypical-Consulting/AdrMcp/dev/.claude/skills/adr-review/SKILL.mdgit clone --depth 1 https://github.com/Atypical-Consulting/AdrMcpWrote 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/atypical-consulting/adrmcp/adr-review)<a href="https://agentmods.dev/skills/atypical-consulting/adrmcp/adr-review"><img src="https://agentmods.dev/badge/skills/atypical-consulting/adrmcp/adr-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/atypical-consulting/adrmcp/adr-review"><img src="https://agentmods.dev/badge/skills/atypical-consulting/adrmcp/adr-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 | $0.00110 | $0.00698 |
| Opus 5 | $0.00055 | $0.00349 |
| Sonnet 5 | $0.00022 | $0.00140 |
| Haiku 4.5 | $0.00011 | $0.00070 |
Grade A, and why
adr-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 9d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reviewing an ADR
You give an ADR a rigorous, fair review — both structural (does it validate?) and substantive (is the decision actually sound and honestly recorded?).
Requires the AdrMcp MCP server (tools
get_adr,validate_adr,detect_conflicts,find_related_adrs,search_adrs). If unavailable, ask the user to connect it, or review the pasted markdown directly against the rubric below.
Workflow
- Load it.
get_adr <id-or-slug>for the full record (or read the draft the user pasted). - Structural pass. Run
validate_adr <id>— report any errors/warnings (missing sections, invalid status, dangling links, superseded-without-replacement). - Conflict/overlap pass. Run
detect_conflictsandfind_related_adrs <id>(orsearch_adrson the topic) to check this decision doesn't silently contradict or duplicate another. Flag any accepted ADR it collides with. - Substantive pass. Score against the rubric below.
- Report as a short verdict + prioritized findings. Offer concrete rewrites, not just
critiques. If the fix is a status/link problem, point to
adr-supersede; if it needs rewriting, offer to apply it viaupdate_adr(preview first).
Rubric
Judge each; call out the ones that fail.
- Significance — Does this decision deserve an ADR at all, or is it noise?
- Context ≠ decision — The context frames forces/constraints and does NOT pre-name the chosen solution. Decision-leakage in the context is the most common defect.
- Falsifiable decision — Stated as a concrete, specific "We will…", not a vague direction. Could someone tell whether it's being followed?
- Real alternatives — Considered options are genuine, with a reason each was rejected. Strawmen ("do nothing", "do it badly") don't count.
- Honest consequences — At least one real trade-off / cost is named. Upside-only records are suspect.
- Traceability — Correct status for its lifecycle stage; links to related/superseded ADRs present; tags identify the area.
- Concision — Reads like a memo. No filler, no unfilled placeholders.
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.
- 9d ago First seen · 50 lines · 110 tokens per session scan A 3eb751cef868
adr-review is a skill published in the GitHub repository Atypical-Consulting/AdrMcp (1 stars, last pushed 19d ago), licensed MIT. It adds 110 tokens to every session and 698 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
bootstrap
Scaffold or retrofit documentation-led conventions (AGENTS.md, CLAUDE.md, CONVENTIONS.md, ADR catalogue, plan/ queue, agent/ coordination) into a repo. Use when the user asks to "set up conventions", "bootstrap ADRs", "scaffold the documentation-led layout", or "add AGENTS.md and a plan queue". Works on fresh repos…
decision-backfill
Use when auditing an existing codebase, documentation set, plans, RFCs, or git history for architecture decisions that were made but never recorded as ADRs, and when triaging potential records before drafting them.
decision-memory
Use when planning, designing, reviewing, or changing code in a repository that keeps ADRs (usually docs/adr) — to load the decisions that already govern the work, check a plan or diff against them, or record a new decision. Also use when a choice feels already-settled and you cannot find where it was settled.
actual
Feature-complete companion for the actual CLI, an ADR-powered CLAUDE.md/AGENTS.md generator. Runs and troubleshoots actual adr-bot, status, auth, config, runners, and models, plus the Actual AI platform surface: login, logout, whoami, and advisor (org-scoped architecture Q&A). Covers all 5 runners (claude-cli…
adr-integration
This skill should be used when the user asks about "ADR integration", "ADR CI/CD", "ADR tooling", "ADR automation", "export ADRs", "ADR documentation site", or needs guidance on integrating ADRs with CI/CD, documentation sites, and other tools.
adr-decision-drivers
This skill should be used when the user asks about "decision drivers", "architectural forces", "quality attributes", "how to identify trade-offs", "non-functional requirements for ADRs", or needs help identifying, documenting, and weighing the forces that influence architectural decisions.