agentmods.dev

review

review is a skill for Claude Code from navapbc/digital-service-orchestra. It costs 84 tokens per session (673 once invoked), scanned A, original, Apache-2.0.

A dispatcher for the project's code-review workflow, which examines the current code changes at a selected level of depth. It follows the repository's review rules before changes are committed.

In plain words
What is it for?
Use it to review uncommitted changes, choose a light, standard, or deep review, and follow the project's review process.
Why use it?
It gives developers a repeatable review step for finding problems in a diff before the changes move forward.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the dso plugin — 37 skills, 4 commands, 53 agents shipped together

not rated 6repo yesterday A scan 84 tokens original Apache-2.0

Good fit Use it to review uncommitted changes, choose a light, standard, or deep review, and follow the project's review process.

Compare 6 skills from other repositories ↓
View source ↗ navapbc/digital-service-orchestra
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add navapbc/digital-service-orchestra
Claude Code
/plugin install dso

Made for: Claude Code.

Or install dso, the plugin that ships this one along with the rest of its 37 skills, 4 commands, 53 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.

agentmods badge for review

README.md
[![agentmods](https://agentmods.dev/badge/skills/navapbc/digital-service-orchestra/review/github.svg)](https://agentmods.dev/skills/navapbc/digital-service-orchestra/review)
Your own site
<a href="https://agentmods.dev/skills/navapbc/digital-service-orchestra/review"><img src="https://agentmods.dev/badge/skills/navapbc/digital-service-orchestra/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.

agentmods 80×15 button for review

Your own site · 80×15
<a href="https://agentmods.dev/skills/navapbc/digital-service-orchestra/review"><img src="https://agentmods.dev/badge/skills/navapbc/digital-service-orchestra/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 673 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00084 $0.00673
Opus 5.5 $0.00034 $0.00269
Sonnet 5.5 $0.00017 $0.00135
Haiku 4.5 $0.00008 $0.00067

Measured 2mo ago against content hash 08f689e73b3c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 2mo 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.

plugins/dso/skills/review/SKILL.md · 50 lines

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.

Review

Shallow entry point for the DSO tiered code review workflow.

DSO_WORKFLOW=$(DSO_DEPRECATION_QUIET=1 ".claude/scripts/dso" read-config.sh dso.workflow 2>/dev/null || true)
if [ "$DSO_WORKFLOW" = "ci-pr" ]; then
    .claude/scripts/dso commit-step skip reviewer-record "dso.workflow=ci-pr"
    .claude/scripts/dso commit-step skip classifier-dispatch "dso.workflow=ci-pr"
    echo "dso.workflow=ci-pr — /dso:review is a no-op (CI runs llm-review)."
    # END the skill — return to caller. Do NOT proceed to "Instructions" below.
    exit 0
fi

The rationalization "but I should run it anyway to be safe" is exactly the failure mode this gate prevents. The pre-commit review-gate and the Layer 2 hook both already skip enforcement under ci-pr; dispatching here adds latency and cost without changing the merge outcome.

What This Does

Loads and executes ${CLAUDE_PLUGIN_ROOT}/docs/workflows/REVIEW-WORKFLOW.md inline. That document is the authoritative review workflow — this skill exists only to provide a /dso:review invocation surface. All review logic, tier selection, agent dispatch, and resolution rules are in REVIEW-WORKFLOW.md.

Usage

/dso:review

Run from the orchestrator context (sprint, commit, or standalone) before committing.

Instructions

IMPORTANT: Do NOT call the Skill tool again or re-invoke /dso:review recursively. Instead:

  1. Read ${CLAUDE_PLUGIN_ROOT}/docs/workflows/REVIEW-WORKFLOW.md now.
  2. Execute its steps verbatim — starting from Step 0 (Clear Stale Review Artifacts).
  3. Follow all HARD-GATE sections and workflow enforcement gates.

Read the full file on GitHub · 50 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. 2mo ago First seen · 50 lines · 84 tokens per session scan A 08f689e73b3c

Subscribe to this mod's changes

review is a skill published in the GitHub repository navapbc/digital-service-orchestra (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 84 tokens to every session and 673 once invoked, about $0.0003 per session on Opus 5.5. 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.

Code review
Related

review compared with skills from other repositories

review next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
reviewnavapbc/digital-service-orchestraSkill6yesterdayApache-2.0A84Claude Code
autoreviewopenclaw/clawhubSkill9.6ktodayMITA17Claude Code, Codex
omh-code-reviewrlaope/oh-my-hermesSkill5.4ktodayMITA49Claude Code, Codex
agent-teams-simplify-and-hardenLeoYeAI/openclaw-master-skillsSkill2.2k5d agoMITA115Claude Code, Codex
revdiff-planumputun/revdiffSkill951todayMITA84Claude Code
re0-mergeLilMGenius/paperthinSkill1.4ktodayMITA51Claude Code, Codex
explore-unknownsdzhng/skillsSkill1.5kyesterdayMITA162Claude Code, Codex