What is qa_review_triple-model?

A four-reviewer code-review workflow that asks Opus, Gemini, Codex, and Kimi K2.5 to inspect code separately, then combines their findings. It is a legacy workflow intended for Claude-only use.

It is for reviewing code or selected project areas, saving each review as a Markdown file, and synthesising the findings into a final analysis.

It helps collect independent review results and bring them together into one report, but it is only appropriate when this specific multi-model review is requested.

How gpt-cmdr/ras-commander configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to gpt-cmdr/ras-commander. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/gpt-cmdr/ras-commander/main/.claude/skills/qa_review_triple-model/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/gpt-cmdr/ras-commander

Made for: Claude Code.

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/gpt-cmdr/ras-commander/qa_review_triple-model/github.svg)](https://agentmods.dev/skills/gpt-cmdr/ras-commander/qa_review_triple-model)

Your own site

<a href="https://agentmods.dev/skills/gpt-cmdr/ras-commander/qa_review_triple-model"><img src="https://agentmods.dev/badge/skills/gpt-cmdr/ras-commander/qa_review_triple-model/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/gpt-cmdr/ras-commander/qa_review_triple-model"><img src="https://agentmods.dev/badge/skills/gpt-cmdr/ras-commander/qa_review_triple-model.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 124 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,057 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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	$0.00124	$0.02057
Opus 5	$0.00062	$0.01028
Sonnet 5	$0.00025	$0.00411
Haiku 4.5	$0.00012	$0.00206

Measured 8d ago against content hash 68ba6d4c1c99, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

qa_review_triple-model 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 8d 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.

.claude/skills/qa_review_triple-model/SKILL.md · 255 lines

How it starts

The opening of the file, as written. The whole thing — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Multi-Model Code Review (4 Models)

Legacy Claude-only orchestration skill. This workflow coordinates external/provider-specific reviewers from Claude. It is excluded from the shared multi-harness corpus and is not part of the standard production QAQC path.

Overview

When the user explicitly requests this legacy provider-mixed workflow, invoke this skill. Launch four independent AI subagents (Opus, Gemini, Codex, and Kimi K2.5) to perform parallel code review. Each agent writes findings to markdown files in a workspace directory, then the orchestrator synthesizes a final report with consensus findings.

Usage

/triple_model_code_review [target] [focus_area]

Examples:

/triple_model_code_review examples/720_precipitation_methods_comprehensive.ipynb "plotting logic"
/triple_model_code_review ras_commander/hdf/HdfResultsPlan.py "return type consistency"
/triple_model_code_review ras_commander/precip/ "API contract validation"
/triple_model_code_review src/auth/login.py "security vulnerabilities"

Workflow

Create Workspace: workspace/{task}QAQC/{opus,gemini,codex,kimi,final}-analysis/
Launch 4 Parallel Subagents:
- Opus (general-purpose, model=opus): Deep reasoning, architecture analysis
- Gemini (code-oracle-gemini): Large context, multi-file pattern analysis
- Codex (code-oracle-codex): Code archaeology, API contract analysis
- Kimi K2.5 (code-oracle-kimi): Edge case detection, test generation focus, QA verification
Handle Model Failures (Graceful Degradation):
- If a model fails or is unavailable, note it and continue
- Synthesis works with 1-4 successful models
- Report which models succeeded/failed to user
Each Agent:
- Reads target files independently
- Writes qaqc-report.md to their subfolder
- Returns file path only (no large text in response)
- If agent fails, creates empty report with error note
Orchestrator Synthesizes:
- Reads all available reports (1-4)
- Identifies consensus findings from successful models
- Creates FINAL_QAQC_REPORT.md with agreement matrix
- Highlights unique insights from each successful model
- Notes which models were unavailable

Read the full file on GitHub · 255 lines

Files

What ships with it

1 file 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.

references/error-handling-and-examples.md 7.2 KB

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.

8d ago First seen · 255 lines · 124 tokens per session scan A 68ba6d4c1c99

Subscribe to this mod's changes

qa_review_triple-model is a skill published in the GitHub repository gpt-cmdr/ras-commander (79 stars, last pushed today), licensed MIT. It adds 124 tokens to every session and 2,057 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 2026-09-03.

Code review

autoreview

Pre-commit/ship code review: Codex default; optional Claude or Pi.

openclaw/clawhub · 20 tokens

omh-code-review

This is a Hermes-native code-review workflow skill.

rlaope/oh-my-hermes · 46 tokens

revdiff-plan

Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…

umputun/revdiff · 84 tokens

code-reviewer

Code review specialist focused on patterns, bugs, security, and performance.

RightNow-AI/openfang · 17 tokens

full-repo-review

Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.

notque/vexjoy-agent · 22 tokens

agent-teams-simplify-and-harden

Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…

LeoYeAI/openclaw-master-skills · 115 tokens

ras-commander: Skill for Claude Code