A code-review workflow for checking a pull request or the current branch against its base branch. A pull request is a proposed code change submitted for review before it is merged.

Use it to review a numbered pull request, review the current branch, apply issue-specific acceptance criteria, and receive an approve-or-reject decision.

It helps find problems and decide whether changes are ready to merge, without changing the code itself.

review — Skill for Claude Code and Codex by The01Geek: A code-review workflow for checking a pull request or…

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/the01geek/prflow/review

Any agent

npx skills add The01Geek/prflow --skill review

Clone the repo

git clone --depth 1 https://github.com/The01Geek/prflow

Made for: Claude Code, Codex.

Or install prflow, the plugin that ships this one along with the rest of its 19 skills, 15 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/skills/the01geek/prflow/review.svg)](https://agentmods.dev/skills/the01geek/prflow/review)

Your own site

<a href="https://agentmods.dev/skills/the01geek/prflow/review"><img src="https://agentmods.dev/badge/skills/the01geek/prflow/review.svg" alt="Measured on agentmods" height="20"></a>

Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 14,467 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.

Model	Per session	Once invoked
Fable 5.1	$0.00123	$0.14467
Opus 5	$0.00062	$0.07234
Sonnet 5	$0.00025	$0.02893
Haiku 4.5	$0.00012	$0.01447

Measured yesterday against content hash 36b9691d01cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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 yesterday.

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.

skills/review/SKILL.md · 346 lines

How it starts

The opening of the file, as written. The whole thing — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/prflow:review — Comprehensive PR Review

You are the review engine orchestrator. Run a four-phase review and present an APPROVE/REJECT verdict.

Input: $ARGUMENTS may contain an optional PR number and/or the flag --issue N; either, both, or neither may be present. Only a bare numeric token binds $PR_NUMBER — never a value following --issue. The flag's value is $ISSUE_OVERRIDE, the caller-supplied issue Phase 0.4 reads acceptance criteria from. If no PR number is given, review the current branch vs its configured base_branch.

Every later PR-mode predicate and every gh command reads $PR_NUMBER — never the raw $ARGUMENTS string.

Engine ground truth (only when the injected block is present)

Some runs prepend a > [!IMPORTANT] engine ground truth block to this prompt, stating the exact --allowed-tools string the run resolved and — where the run has a reviewed commit — the CI results observed for it. Everything below is conditioned on that block being present, and each numbered item on the block section it reads: on the inline tier (/prflow:review-and-fix, and the review engine as executed by an implement run's review phase) the block carries the permitted-commands and command-shape sections but no CI section, so item 2 applies in full while items 1, 3 and 4 stay inert.

On the inline tier the test evidence is the orchestrator's own in-environment suite/lint results for the current HEAD — never a CI conclusion. No inline-tier arm waits for, requires, or cites one. Where it observed the suite/lint pass in-env, that is the discharged test evidence; where it could not run them, the verdict says the test evidence is missing rather than deferring to CI.

When the block IS present:

Its CI signals are the authoritative test evidence for the reviewed commit. DevFlow read those conclusions from the GitHub API for that exact commit; cite them as the result of the checks they name — a failure or in_progress as readily as a success. Do not re-derive them by running builds or tests: Phase 2 verifies the checklist, not the test suite.

Read the full file on GitHub · 346 lines

Files

What ships with it

9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

yesterday Changed 36b9691d01cb
5d ago First seen · 346 lines · 123 tokens per session scan A 93d5d830279e

Subscribe to this mod's changes

review is a skill published in the GitHub repository The01Geek/prflow (115 stars, last pushed 5d ago), licensed MIT. It adds 123 tokens to every session and 14,467 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 2026-08-30.

Code review ai-agents automation claude-code developer-tools plugin

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

/prflow:review — Comprehensive PR Review

Engine ground truth (only when the injected block is present)

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

taiyi-ui-design

flow-next-resolve-pr

flow-next-tracker-sync

taiyi-evolve

taiyi-diagram-c4

flow-next-prime