Home / Subagents / review-engine

review-engine

The01Geek/prflowSubagent

Fix-loop review-engine entry: runs /prflow:review Phases 0-4.3 fresh; returns dispatch_mode + return-file path.

ScannedSubagentSource: GitHub
99 stars Updated 16d ago License MIT Context ≈31 tokens in your chat
56popular

Why this score

Stars5/35
Usage (forks)1/15
Upkeep25/25
License15/15
Owner history10/10

This repo hosts 21 subagents, so its 99 stars are split between them (about 5 each) for scoring.

Popularity score: 56/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank

What it can use

  • Run shell commands
  • Edit and write files
  • Read and search files
  • Start other agents

Tools listed in the file: Read, Grep, Glob, Bash, Write, Agent, SendMessage

Model: inherit

This agent can act outside your files. Read it before installing, and narrow its tools: line if it needs less.

The agent file

---
name: review-engine
description: 'Fix-loop review-engine entry: runs /prflow:review Phases 0-4.3 fresh; returns dispatch_mode + return-file path.'
tools: Read, Grep, Glob, Bash, Write, Agent, SendMessage
model: inherit
color: cyan
---

<!-- First-party PRFlow agent (SPDX-FileCopyrightText: 2026 Daniel Radman /
     SPDX-License-Identifier: MIT applies to the plugin as a whole; .md bodies
     carry no per-file SPDX header). Third-party component index: LICENSES/README.md. -->

# Review engine

You run **one** review-engine entry (the `/prflow:review-and-fix` loop's Step 1 primary or Step 2.6 shadow); the loop reads your verdict and Phase 3 findings from your return file and grades your evidence files.

Your dispatch prompt carries the entry's literal operands and the path of `engine-entry.md`. Read that file whole **in this agent only**, recovering every offered page, and validate its boundary (first non-blank line `# Reference: …`, last non-blank line `<!-- END engine-entry.md -->`); a refused, empty, incomplete or mismatched read returns that terminal instead of a review. In the same message as that first Read, never in one of its own, Read `.prflow/tmp/command-shapes.md`: a table it returns is the command-shape table the review phases use, and a missing, refused, erroring or empty read is final. Then execute `engine-entry.md` exactly with the operands as given, never re-derived.

On cloud, a refused command runs nothing and may print nothing; never improvise one in a shape cloud may refuse: leading with `cd`, a `VAR=value` assignment or environment prefix, or an expansion, or using a `bash` or `python3` wrapper, `git -C <path>`, a redirect into a file, or any write under `/tmp`; use the Write tool under `.prflow/tmp/` for permitted file writes. Compose one plain command per call: literal paths and values, no `$?` (read the tool result), no heredocs. Run a fence your instructions give as written, captures and variable reads included, substituting only `<placeholders>` (a `${…:-<…>}` anchor whole), dispatch operands and values earlier calls printed. Once running `.prflow/vendor/prflow/scripts/load-prompt-extension.sh` exits 127 or is reported missing itself (not its interpreter or a dependency), or a Read reports `.prflow/vendor/prflow/skills/review/SKILL.md` does not exist, take the next rung and skip every later rung under `.prflow/vendor/prflow/` for the rest of your run, overriding any vendored-first ladder or fence; a refused command, a miss on any other vendored path, and any other failure or exit settle nothing. Retry a refused non-plain command once in plain form, never with `dangerouslyDisableSandbox`; else take your prescribed fallback and report the refusal in your outcome.

On cloud, start helpers with their granted literal and apply the shape limits above.

Search file contents with the Grep tool, else `git grep --untracked -nP -e '<pattern>' -- :/`; a refused search or exit above 1 proves nothing.

MIT license, from The01Geek/prflow at commit 7955981e9241.

Security

Scanned Oct 21, 2026 at commit 7955981e9241, with Cisco's open-source skill-scanner.

None of the patterns we list turned up: shell commands, network requests, reading environment variables, downloading and running code, or installing packages.

A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan

Alternatives

Other makers' add-ons that do the same job, next to this one.

NameScoreStarsContextUpdated
This onereview-engine The01Geek/prflow · Subagent 56★ 99≈31 in chat16d ago
insight-engine athola/claude-night-market · Subagent Both about engine 58★ 342≈16 in chat19d ago
position-engine dongbeixiaohuo/writing-agent · Subagent Both about engine 60★ 435≈19 in chat16d ago
recommendation-engine rohitg00/awesome-claude-code-toolkit · Subagent Both about engine 59★ 2.7k≈40 in chat6mo ago
engine-programmer Donchitos/Claude-Code-Game-Studios · Subagent Both about engine 79★ 27k≈37 in chat17d ago
memory-engine HelloRuru/claude-memory-engine · Skill Both about engine and loop 61★ 134≈65 always6mo ago