kavo: Command for Claude Code

.claude/commands/merge.md

merge is a command for Claude Code from kavo-labs/kavo. It costs 17 tokens per session (899 once invoked), scanned A, original, MIT.

A command that completes a GitHub pull request by checking its status, merging it with a squash commit, deleting the branch, and updating the main branch. A pull request is a proposed code change awaiting review.

In plain words
What is it for?
Use it to verify CI, inspect merge readiness, merge an approved pull request, remove its branch, and return to updated main.
Why use it?
It prevents merging when required checks are failing, still running, or the branch has conflicts.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is kavo-labs/kavo's own configuration. It tells Claude Code how to work on kavo 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 kavo configures →

Reuse

Borrowing it

Nothing to install: this file belongs to kavo-labs/kavo. 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/kavo-labs/kavo/main/.claude/commands/merge.md
Clone the repo
git clone --depth 1 https://github.com/kavo-labs/kavo

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 merge

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/kavo-labs/kavo/merge"><img src="https://agentmods.dev/badge/commands/kavo-labs/kavo/merge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 899 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 $0.00017 $0.00899
Opus 5 $0.00009 $0.00449
Sonnet 5 $0.00003 $0.00180
Haiku 4.5 $0.00002 $0.00090

Measured 7d ago against content hash a5956fc00e4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

merge 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.

.claude/commands/merge.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context

  • Branch: !git rev-parse --abbrev-ref HEAD
  • Working tree: !git status --short
  • PR: !gh pr view $ARGUMENTS --json number,title,state,isDraft,mergeable,mergeStateStatus,reviewDecision,url 2>/dev/null || echo "NO PR"
  • Checks: !gh pr checks $ARGUMENTS 2>/dev/null || echo "no checks reported"

Your task

Close the loop on this PR. Argument: $ARGUMENTS

  1. Refuse to merge if any of these hold. Report which one and stop:

    • there is no matching PR;
    • the PR is still a draft;
    • any required check is failing or still running — wait for it, do not merge past it;
    • mergeable is false, or there are conflicts with main;

    If the only problem is that checks are still running, say so and offer to wait rather than merging blind.

  2. Say what you are about to merge — PR number, title, commit count, and the issue it closes — and get the user's go-ahead before the merge itself. This is the irreversible step.

  3. Merge with squash, keeping history linear and one commit per issue. Always pass an authored --subject and --body — never let gh fall back to its default squash body, which is the concatenated list of branch commit messages (* feat(scope): … bullets and all). release-please parses the whole merged message, and a body full of pseudo-headers and nested call(inner()) code spans has silently defeated its parser before (fix commit could not be parsed → the commit is dropped from the changelog and triggers no bump; commit 9fa1434 / #354).

    gh pr merge <n> --squash --delete-branch \
      --subject "feat(core): …" \
      --body "$(cat <<'EOF'
    One or two plain-prose paragraphs summarizing the change.
    
    Refs #<n>
    EOF
    )"
    

    Write the subject as a Conventional Commit matching this repo's style (feat(core): …). Keep the body plain prose: no * type(scope): bullet lines, and rephrase any outer(inner()) nesting (metadataFor of relation.target(), not metadataFor(relation.target())).

Read the full file on GitHub · 85 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. 7d ago First seen · 85 lines · 17 tokens per session scan A a5956fc00e4e

Subscribe to this mod's changes

merge is a command published in the GitHub repository kavo-labs/kavo (14 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 899 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 2026-09-02.