review

review is a command for Claude Code from dork-labs/dorkos. It costs 21 tokens per session (1,876 once invoked), scanned A, original, MIT.

A command for reviewing proposed Architecture Decision Records (ADRs), which document important technical choices, and moving them through their lifecycle.

In plain words
What is it for?
Use it after implementing a specification, during ADR maintenance, or to review all proposed records, records for one specification, or a single ADR number.
Why use it?
It helps remove stale or trivial proposals and mark implemented decisions as accepted without repeatedly reviewing decisions that are already accepted.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; names the AskUserQuestion tool; mentions AGENTS.md.

Part of the flow plugin — 33 skills, 42 commands, 5 agents, 4 hooks, 5 plugins shipped together

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.

agentmods
npx agentmods add commands/dork-labs/dorkos/review
Clone the repo
git clone --depth 1 https://github.com/dork-labs/dorkos

Made for: Claude Code.

Or install flow, the plugin that ships this one along with the rest of its 33 skills, 42 commands, 5 agents, 4 hooks, 5 plugins.

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 review

README.md
[![agentmods](https://agentmods.dev/badge/commands/dork-labs/dorkos/review.svg)](https://agentmods.dev/commands/dork-labs/dorkos/review)
Your own site
<a href="https://agentmods.dev/commands/dork-labs/dorkos/review"><img src="https://agentmods.dev/badge/commands/dork-labs/dorkos/review.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,876 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00021 $0.01876
Opus 5 $0.00010 $0.00938
Sonnet 5 $0.00004 $0.00375
Haiku 4.5 $0.00002 $0.00188

Measured 6d ago against content hash 766353ac12a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

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.

.claude/commands/adr/review.md · 212 lines

How it starts

The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review ADRs for Lifecycle Progression

Argument: $ARGUMENTS


Purpose

Move ADRs past the "proposed" stage. ADRs are born proposed (or accepted, via /adr:create and /adr:from-spec); this command handles the rest of the lifecycle: proposed → accepted | deprecated | superseded | archived.

This command never re-examines an accepted ADR — that is /adr:audit's job (accepted ADRs rot silently as the codebase moves on; the audit re-verifies them against code and stamps lastVerified).

When to run:

  • After completing a spec implementation
  • When the proposed ADR count exceeds 50
  • Periodically (monthly) for general maintenance
  • When a SessionStart hook suggests it

Steps

Step 1: Determine Scope

Parse $ARGUMENTS to decide what to review:

Argument Scope
--all or empty All proposed ADRs
A spec slug (e.g., relay-core-library) Only ADRs linked to that spec
An ADR number (e.g., 43 or 0043) Single ADR

Step 2: Load Context

  1. Read decisions/manifest.json — filter for proposed ADRs matching scope
  2. Read specs/manifest.json — get spec statuses for cross-referencing
  3. If reviewing all, group proposed ADRs by specSlug

Step 3: Evaluate Each ADR (or Group)

For each proposed ADR, apply these checks in order (first match wins):

Check A: Is the linked spec implemented?

If the ADR has a specSlug and that spec's status is implemented or completed in the spec manifest:

  • Verify the decision is reflected in code — do a quick grep/glob for the pattern or technology described in the ADR
  • If confirmed: Recommend → accepted
  • If the code diverged from the decision: Recommend → deprecated (note what actually happened)
Check B: Is the linked spec abandoned?

If the spec is still ideation and was created more than 30 days ago, OR the spec slug doesn't exist in the spec manifest:

Read the full file on GitHub · 212 lines

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. 6d ago First seen · 212 lines · 21 tokens per session scan A 766353ac12a3

Subscribe to this mod's changes

review is a command published in the GitHub repository dork-labs/dorkos (9 stars, last pushed today), licensed MIT. It adds 21 tokens to every session and 1,876 once invoked, about $0.0001 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.