A code-review command that examines changed code in a branch, commit, or pull request and produces a structured list of findings. A pull request is a proposed change for others to review before it is merged.

It reviews uncommitted edits, recent commits, branches, or pull requests, reads the surrounding files, assigns confidence to findings, and can optionally apply fixes or post comments on a pull request.

It gives reviewers a consistent way to look for defects, dead code, security concerns, architecture problems, and project-rule violations instead of relying only on a quick diff.

code-review — Command for Claude Code by acaprino/daodan

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.

Clone the repo

git clone --depth 1 https://github.com/acaprino/daodan

Made for: Claude Code.

Or install senior-review, the plugin that ships this one along with the rest of its 3 skills, 3 commands, 12 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/acaprino/daodan/code-review/github.svg)](https://agentmods.dev/commands/acaprino/daodan/code-review)

Your own site

<a href="https://agentmods.dev/commands/acaprino/daodan/code-review"><img src="https://agentmods.dev/badge/commands/acaprino/daodan/code-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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/acaprino/daodan/code-review"><img src="https://agentmods.dev/badge/commands/acaprino/daodan/code-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,112 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.01112
Opus 5.5	$0.00000	$0.00445
Sonnet 5.5	$0.00000	$0.00222
Haiku 4.5	$0.00000	$0.00111

Measured 9d ago against content hash 432a7adaf907, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

code-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.

exports/claude/plugins/senior-review/commands/code-review.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

code-review

Execution harness

Selected topology: native-team. Use native Agent Teams when they are enabled in this session; otherwise dispatch the same roles as isolated subagents. Both paths satisfy the same contract, and which one answered changes nothing a reader of the report can observe. Declared worker isolation: required.

Harness obligations, none of them optional:

Every dispatched worker runs in its own context and reads only coordinator-declared inputs. Independent reviewers never read peer results before their own delivery; no worker runs in the coordinator's context.
Follow the dispatch plan below in phase order. A phase starts only after every phase it needs has closed, and a phase closes only when every worker it dispatched is recorded delivered or failed. A missing result is a recorded failure, never a silently shorter report.
Dispatch only roles from this set, as the phase graph or loaded method requires: abstraction-architect:abstraction-architect-agent, code-auditor, data-integrity-auditor, platform-engineering:platform-reviewer, premise-auditor, project-protocol:isolated-worker, react-development:react-performance-optimizer, resource-lifecycle-auditor, security-auditor, temporal-resilience-auditor, testing:test-suite-auditor, typescript-development:type-safety-auditor, ui-race-auditor
Workers may write only intermediate reports explicitly assigned by the coordinator. The final report artifact has one exclusive owner in its declaring phase.

Dispatch plan:

run: runs in the orchestrating context; produces artifact:code-review-report.

Role bindings:

abstraction-architect:abstraction-architect-agent: dispatch the installed abstraction-architect:abstraction-architect-agent agent by its qualified identity.
platform-engineering:platform-reviewer: dispatch the installed platform-engineering:platform-reviewer agent by its qualified identity.
project-protocol:isolated-worker: dispatch the installed project-protocol:isolated-worker agent by its qualified identity.
react-development:react-performance-optimizer: dispatch the installed react-development:react-performance-optimizer agent by its qualified identity.
code-auditor: dispatch the installed senior-review:code-auditor agent by its qualified identity.
data-integrity-auditor: dispatch the installed senior-review:data-integrity-auditor agent by its qualified identity.
premise-auditor: dispatch the installed senior-review:premise-auditor agent by its qualified identity.
resource-lifecycle-auditor: dispatch the installed senior-review:resource-lifecycle-auditor agent by its qualified identity.
security-auditor: dispatch the installed senior-review:security-auditor agent by its qualified identity.
temporal-resilience-auditor: dispatch the installed senior-review:temporal-resilience-auditor agent by its qualified identity.
ui-race-auditor: dispatch the installed senior-review:ui-race-auditor agent by its qualified identity.
testing:test-suite-auditor: dispatch the installed testing:test-suite-auditor agent by its qualified identity.
typescript-development:type-safety-auditor: dispatch the installed typescript-development:type-safety-auditor agent by its qualified identity.
Method-owned inline workers use only project-protocol:isolated-worker. Give each the full task, owned scope, authorization and budget, plus its expected report path. This permission exposes no other registry role.

Read the full file on GitHub · 65 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.

9d ago Changed · -309 lines · -155 tokens per session 432a7adaf907
14d ago Changed 276e812057e1
16d ago Changed · -2 lines df36b89dab58
1mo ago First seen · 376 lines · 155 tokens per session scan A f75b455f2205

Subscribe to this mod's changes

code-review is a command published in the GitHub repository acaprino/daodan (9 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,112 tokens. 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 2026-09-05.

Code review

code-review

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

code-review

Execution harness

What this file has done since we first saw it

Other commands, from other repositories

refactor

review-branch

init

merge-conflict-analysis

boot

repo-audit