ensemble-review

ensemble-review is a skill for Claude Code from key4ng/lite-cc. It costs 19 tokens per session (337 once invoked), scanned A, original, MIT.

A code-review workflow that asks three different AI models to inspect the current Git branch’s changes in parallel, then combines their findings into one report.

In plain words
What is it for?
Reviewing a diff for bugs, security issues, performance problems, and readability concerns, with file locations and severity levels.
Why use it?
Comparing several independent reviews can separate issues multiple reviewers agree on from findings that need manual checking.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the ensemble-review plugin — 1 skill shipped together

Good fit Reviewing a diff for bugs, security issues, performance problems, and readability concerns, with file locations and severity levels.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/key4ng/lite-cc/ensemble-review
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.

Any agent
npx skills add key4ng/lite-cc --skill ensemble-review
Clone the repo
git clone --depth 1 https://github.com/key4ng/lite-cc

Made for: Claude Code.

Or install ensemble-review, the plugin that ships this one along with the rest of its 1 skill.

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 ensemble-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/key4ng/lite-cc/ensemble-review.svg)](https://agentmods.dev/skills/key4ng/lite-cc/ensemble-review)
Your own site
<a href="https://agentmods.dev/skills/key4ng/lite-cc/ensemble-review"><img src="https://agentmods.dev/badge/skills/key4ng/lite-cc/ensemble-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 337 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.
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 5.1 $0.00019 $0.00337
Opus 5 $0.00010 $0.00169
Sonnet 5 $0.00004 $0.00067
Haiku 4.5 $0.00002 $0.00034

Measured 7d ago against content hash 635f5e96c3b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ensemble-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 7d 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.

examples/ensemble-review/pipeline/ensemble-review/SKILL.md · 40 lines

What it actually says

Ensemble Review

Steps

  1. Get the diff to review:

    • Run git diff main...HEAD via bash to get the current branch's changes
    • If no changes found, tell the user there are no changes to review
  2. Spawn 3 subagents, each with a different model. Give each the diff as part of the prompt:

    Models to use:

    • oci/openai.gpt-5.4
    • oci/google.gemini-2.5-flash
    • oci/xai.grok-code-fast-1

    Use spawn_subagent for each model with this prompt (include the diff inline):

    Review this code diff. Identify bugs, security issues, performance problems, and readability concerns. For each issue, provide the file, line, severity (critical/warning/info), and a brief explanation.

    Use tools: ["read_file", "list_files", "grep"] so reviewers can check surrounding code.

  3. Collect all 3 reviews. Note any subagents that failed and which models succeeded.

  4. Synthesize a unified report:

    • Consensus issues: flagged by 2+ models (high confidence)
    • Unique findings: flagged by only 1 model (review manually)
    • Summary: overall assessment combining all perspectives
  5. Present the report to the user.

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. 7d ago First seen · 40 lines · 19 tokens per session scan A 635f5e96c3b1

Subscribe to this mod's changes

ensemble-review is a skill published in the GitHub repository key4ng/lite-cc (4 stars, last pushed 5mo ago), licensed MIT. It adds 19 tokens to every session and 337 once invoked, about $0.0001 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.