review-panel

review-panel is a skill for Claude Code from raine/consult-llm. It costs 39 tokens per session (2,555 once invoked), scanned A, original, MIT.

A code-review workflow that asks several AI models to inspect an existing set of changes, then combines their feedback into a prioritized list.

In plain words
What is it for?
It helps review a Git diff, identify serious or likely problems, and optionally apply clear, small fixes.
Why use it?
It reduces the chance that one reviewer misses a bug and removes duplicate or poorly prioritized comments.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md.

Good fit It helps review a Git diff, identify serious or likely problems, and optionally apply clear, small fixes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/raine/consult-llm/review-panel
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 raine/consult-llm --skill review-panel
Clone the repo
git clone --depth 1 https://github.com/raine/consult-llm

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.

agentmods badge for review-panel

README.md
[![agentmods](https://agentmods.dev/badge/skills/raine/consult-llm/review-panel/github.svg)](https://agentmods.dev/skills/raine/consult-llm/review-panel)
Your own site
<a href="https://agentmods.dev/skills/raine/consult-llm/review-panel"><img src="https://agentmods.dev/badge/skills/raine/consult-llm/review-panel/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.

agentmods 80×15 button for review-panel

Your own site · 80×15
<a href="https://agentmods.dev/skills/raine/consult-llm/review-panel"><img src="https://agentmods.dev/badge/skills/raine/consult-llm/review-panel.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,555 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 warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 183
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00039 $0.02555
Opus 5 $0.00019 $0.01277
Sonnet 5 $0.00008 $0.00511
Haiku 4.5 $0.00004 $0.00255

Measured 10d ago against content hash 2794d2f73f1e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

review-panel 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 10d 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.

skills/review-panel/SKILL.md · 215 lines

How it starts

The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run a standalone multi-model review of a diff. Reviewers receive the same prompt independently; the agent synthesizes duplicate findings into a prioritized checklist and can optionally apply unambiguous fixes.

Load the consult-llm skill before proceeding — it defines the invocation contract (stdin heredoc, flags, output format, multi-model calls). Do not call the CLI without loading it first.

Available models

Selectors resolvable in this environment (depends on configured API keys):

!`consult-llm models`

Argument handling

Arguments: $ARGUMENTS

Check $ARGUMENTS for flags:

Reviewer flags: any --<selector> from the Models block above selects that reviewer (e.g. --gemini, --openai, --deepseek). Repeat for multiple. Translate model flags and defaults according to the loaded consult-llm skill's model-selection rules.

Diff flags:

  • --diff-base <ref> — base ref for review. Default is auto-detected so a feature branch is reviewed in full (see Phase 1 for the resolution order). Pass an explicit ref (HEAD, HEAD~3, a branch name, a SHA) to override.
  • --fix — opt in to applying unambiguous localized fixes for must-fix findings. Default is read-only report.

Strip all flags from arguments to get any user-supplied review focus. If no focus remains, review for correctness, regressions, security, and maintainability.

Phase 0: Load consult-llm skill

Load it now. Follow its invocation contract for all CLI calls in this workflow.

Phase 1: Identify changed files

Resolve <diff-base>:

  1. If --diff-base was passed, use it as-is.
  2. Otherwise detect the repo's main branch (git symbolic-ref refs/remotes/origin/HEAD → strip refs/remotes/origin/, fall back to main then master) and use git merge-base HEAD <main> (prefer origin/<main> if it exists locally, else the local <main>). The branch may not be pushed and may have no upstream — don't rely on @{upstream}.
  3. If HEAD has no divergence from the resolved base (already on the main branch), fall back to <diff-base>=HEAD so the skill still reviews uncommitted changes.
  4. Stacked branches and feature-off-feature workflows are not auto-detected — pass --diff-base <parent> explicitly in those cases.

Read the full file on GitHub · 215 lines

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. 10d ago First seen · 215 lines · 39 tokens per session scan A 2794d2f73f1e

Subscribe to this mod's changes

review-panel is a skill published in the GitHub repository raine/consult-llm (133 stars, last pushed 2d ago), licensed MIT. It adds 39 tokens to every session and 2,555 once invoked, about $0.0002 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.