phase-review

phase-review is a skill for Claude Code, Codex from yarlson/yarstack. It costs 32 tokens per session (297 once invoked), scanned A, original, MIT.

A review skill for finding structural problems introduced by a validated code change, such as duplication, unclear ownership, loose types, or unnecessary indirection. It focuses on maintainability after correctness has already been checked.

In plain words
What is it for?
Use it after phase validation to inspect changed files, assess maintainability, make safe scoped corrections when authorized, and rerun affected checks.
Why use it?
It helps catch code-structure regressions without expanding the review into unrelated defects or new behavior.

Skill for Claude CodeCodex

Part of the yarstack plugin — 38 skills 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 skills/yarlson/yarstack/phase-review
Any agent
npx skills add yarlson/yarstack --skill phase-review
Clone the repo
git clone --depth 1 https://github.com/yarlson/yarstack

Made for: Claude Code, Codex.

Or install yarstack, the plugin that ships this one along with the rest of its 38 skills.

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 phase-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/yarlson/yarstack/phase-review.svg)](https://agentmods.dev/skills/yarlson/yarstack/phase-review)
Your own site
<a href="https://agentmods.dev/skills/yarlson/yarstack/phase-review"><img src="https://agentmods.dev/badge/skills/yarlson/yarstack/phase-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 297 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 $0.00032 $0.00297
Opus 5 $0.00016 $0.00148
Sonnet 5 $0.00006 $0.00059
Haiku 4.5 $0.00003 $0.00030

Measured 4d ago against content hash c2998eb3d424, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

phase-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 4d 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/yarstack/skills/phase-review/SKILL.md · 24 lines

What it actually says

Phase Structural Review

Own a narrow maintainability pass after correctness has been established.

Workflow

  1. Read the selected contract, applicable repository rules, final diff, and changed units.
  2. Identify only complexity, duplication, unclear ownership, loose types, or unnecessary indirection introduced or materially worsened by the selected change.
  3. Use crap-index-assess when the repository's configured CRAP check covers changed methods or the phase was intended to reduce their CRAP risk. Treat score changes as supporting evidence, not a structural verdict.
  4. Fix a finding only when the parent implementation request authorizes scoped edits and the correction is clearly behavior-preserving.
  5. Report a worthwhile correction when it requires non-trivial restructuring or broader authority; do not expand scope during the review.
  6. Rerun affected checks after every edit.

Correctness belongs to phase-validate; general read-only defect review to code-review; test sufficiency to test-gap-review; documentation accuracy to docs-drift-review; and specialized risks to their owning reviewers.

Do not add behavior, pursue unrelated cleanup, use subjective file-size thresholds, or continue until no imaginable simplification remains.

Finish when structural regressions introduced by the change are fixed or reported with their scope and risk.

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. 4d ago First seen · 24 lines · 32 tokens per session scan A c2998eb3d424

Subscribe to this mod's changes

phase-review is a skill published in the GitHub repository yarlson/yarstack (3 stars, last pushed 7d ago), licensed MIT. It adds 32 tokens to every session and 297 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 2026-08-31.

Related

Other skills, from other repositories

opensrc

Fetch dependency source code to give AI agents deeper implementation context. Use when the agent needs to understand how a library works internally, read source code for a package, fetch implementation details for a dependency, or explore how an npm/PyPI/crates.io package is built. Triggers include "fetch source for"…

vercel-labs/opensrc · 103 tokens

release-cli

Release a new version of the tokenmaxxing CLI to npm. Use when explicitly asked to release or publish @851-labs/tokenmaxxing, including checking main, bumping apps/cli/package.json, updating CHANGELOG.md, committing, tagging cli-vX.Y.Z, pushing, monitoring generated native package publishing, and smoke testing the…

851-labs/tokenmaxxing · 73 tokens

audit-plan-implementation

Independently audit a task attempt or completed run against a frozen plan, checking ownership, evidence, acceptance, and final readiness.

avksp/agent-lifecycle-kit · 31 tokens

agent-first-planning

Create or revise production-ready SDD plans for agent execution, including clarification, specification, freeze inputs, ownership, budgets, and evidence contracts.

avksp/agent-lifecycle-kit · 33 tokens

ship-mobile-app

Build, change, debug, and prepare production mobile apps across domain meaning, local and server state, lifecycle, platform, and release boundaries. Use for non-trivial Flutter, React Native, iOS, or Android work involving persistence, sync, auth, offline behavior, notifications, permissions, native integrations…

aiopshwang/ship-mobile-app · 103 tokens

verify-regression-tests

Verify that a regression test actually detects the defect it claims to guard against. Use after adding or reviewing a bug-fix guard, reproducing the original failure after a fix, or investigating a suspiciously green regression test. Do not use for general TDD, broad test-suite audits, mutation-score optimization…

aiopshwang/verify-regression-tests · 75 tokens