liam: Command for Claude Code

.claude/commands/review-renovate.md

review-renovate is a command for Claude Code from liam-hq/liam. It costs 11 tokens per session (713 once invoked), scanned A, original, Apache-2.0.

A procedure for reviewing and merging Renovate pull requests. Renovate is a tool that automatically creates pull requests to update dependencies.

In plain words
What is it for?
Use it to inspect open Renovate pull requests, review their release notes and checks, run project validation, and update the automerge setup when appropriate.
Why use it?
It provides a consistent way to check automated updates, investigate failed checks, judge the risk of version changes, and prepare fixes when needed.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is liam-hq/liam's own configuration. It tells Claude Code how to work on liam itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything liam configures →

About the project

Liam ERD is a tool that turns database schemas into interactive entity-relationship diagrams, visual maps showing tables and their relationships. It helps people understand and document database structures, including complex schemas.

liam-hq/liam · 5,105 stars · on GitHub · liambx.com

Reuse

Borrowing it

Nothing to install: this file belongs to liam-hq/liam. 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/liam-hq/liam/main/.claude/commands/review-renovate.md
Clone the repo
git clone --depth 1 https://github.com/liam-hq/liam

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-renovate

README.md
[![agentmods](https://agentmods.dev/badge/commands/liam-hq/liam/review-renovate/github.svg)](https://agentmods.dev/commands/liam-hq/liam/review-renovate)
Your own site
<a href="https://agentmods.dev/commands/liam-hq/liam/review-renovate"><img src="https://agentmods.dev/badge/commands/liam-hq/liam/review-renovate/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-renovate

Your own site · 80×15
<a href="https://agentmods.dev/commands/liam-hq/liam/review-renovate"><img src="https://agentmods.dev/badge/commands/liam-hq/liam/review-renovate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 713 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 $0.00011 $0.00713
Opus 5 $0.00005 $0.00357
Sonnet 5 $0.00002 $0.00143
Haiku 4.5 $0.00001 $0.00071

Measured 9d ago against content hash 3c1af2cfe85d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

review-renovate 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 9d 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/commands/review-renovate.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task

Review renovate PRs following this workflow:

flowchart TD
    Start([Start]) --> ListPR["gh pr list --author=app/renovate --state open"]
    
    ListPR --> SelectPR{Select PR}
    SelectPR --> ViewPR[gh pr view to check PR details]
    
    ViewPR --> CheckCI{CI passing?}
    CheckCI -->|No| Investigation[Investigate issues]
    CheckCI -->|Yes| VersionType{Version change type}
    
    Investigation --> Checkout[gh pr checkout to get locally]
    Checkout --> Install[pnpm install to update dependencies]
    Install --> RunTests[Run pnpm test/build/lint]
    RunTests --> FixIssue{Fixable?}
    FixIssue -->|Yes| ApplyFix[Apply fix]
    FixIssue -->|No| Comment[Report with gh pr comment]
    
    ApplyFix --> CommitPush[git commit & push]
    CommitPush --> WaitCI[Wait for CI re-run]
    WaitCI --> CheckCI
    
    VersionType -->|patch| LowRisk[Low risk]
    VersionType -->|minor| MediumRisk[Medium risk]
    VersionType -->|major| HighRisk[High risk]
    
    LowRisk --> CheckChangelog[Check CHANGELOG/release notes]
    MediumRisk --> CheckChangelog
    HighRisk --> DetailedReview[Detailed review required]
    
    DetailedReview --> CheckChangelog
    CheckChangelog --> CheckSecurity{Security fix?}
    
    CheckSecurity -->|Yes| Priority[High priority]
    CheckSecurity -->|No| CheckDeps{Check dependencies}
    Priority --> CheckDeps
    
    CheckDeps --> PeerDeps{Peer deps compatibility OK?}
    PeerDeps -->|Yes| CheckAutomerge{Automerge-enabled<br/>package?}
    PeerDeps -->|No| Investigation
    
    CheckAutomerge -->|Yes| UpdateConfig[Update renovate.json5]
    CheckAutomerge -->|No| AddApprovalComment[Add approval comment with gh pr comment]
    
    UpdateConfig --> CreatePR[Create automerge config PR]
    CreatePR --> AddApprovalComment
    
    AddApprovalComment --> ApprovePR[Approve PR with gh pr review --approve]
    ApprovePR --> AddToMergeQueue[Add to merge queue: gh pr merge --auto]
    
    AddToMergeQueue --> NextPR{Other PRs exist?}
    
    Comment --> Reject[Reject/postpone PR]
    
    Reject --> NextPR
    NextPR -->|Yes| SelectPR
    NextPR -->|No| End([Complete])

Read the full file on GitHub · 80 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. 9d ago First seen · 80 lines · 11 tokens per session scan A 3c1af2cfe85d

Subscribe to this mod's changes

review-renovate is a command published in the GitHub repository liam-hq/liam (5,105 stars, last pushed today), licensed Apache-2.0. It adds 11 tokens to every session and 713 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 2026-08-30.