ryderfreeman4logos/cli-sub-agent/review-loop

Claude Code and agent skill by ryderfreeman4logos/cli-sub-agent

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Use when: iterative review-fix loop until csa review --diff is clean

Install

npx vskill@latest install ryderfreeman4logos/cli-sub-agent/review-loop

SKILL.md

Review Loop

Bounded diagnostic review-fix front end. It may run at most 2 identical serial review → fix → review rounds. If the branch is still not clean, the serial loop MUST stop and change topology: freeze HEAD, fan out read-only discovery by semantic scope × lens, verify/deduplicate, cluster root causes, batch repairs, and finish with a fresh whole-range clean-room gate. Reaching the budget never authorizes PASS, push, or merge.

Usage

bash
csa run --sa-mode true --skill review-loop "Review and fix current changes"
SA Mode Propagation (MANDATORY)

When operating under SA mode (e.g., dispatched by /sa or any autonomous workflow), ALL `csa` invocations MUST include `--sa-mode true`. This includes csa run, csa review, csa debate, and any other execution commands. Omitting --sa-mode at root depth causes a hard error; passing false when the caller is in SA mode breaks prompt-guard propagation.

Behavior

  1. Reviews current diff with csa review --diff
  2. If issues found: fixes them and re-reviews (up to MAX_ROUNDS)
  • Multi-finding optimization: When 2+ findings affect different files,

uses parallel-fix pattern (parallel RECON / serial EDIT) for faster fix rounds.

  1. If clean: exits successfully
  2. If max rounds are reached: keeps the branch blocked, persists remaining

findings, and escalates to convergence topology; never returns PASS merely because the serial budget is exhausted

Variables

  • MAX_ROUNDS: Maximum review-fix iterations (default: 2)

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
5

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/ryderfreeman4logos/cli-sub-agent/review-loop/badge)](https://verified-skill.com/skills/ryderfreeman4logos/cli-sub-agent/review-loop)

Something wrong with this skill or its page? Tell us.