squash-message

squash-message is a command for Claude Code from scenario-labs/skills. It costs 0 tokens per session (337 once invoked), scanned A, original, MIT.

A command that writes one squash commit message for all changes in the current pull request (PR). It compares the branch with the main branch and formats the result using the repository’s commit rules.

In plain words
What is it for?
Use it when preparing a PR for squash merging, especially when the project requires conventional commit format, a structured body, and a co-author line.
Why use it?
It removes the need to review every development commit and write a summary by hand. The message reflects the final changes instead of temporary fixes made during development.

Command for Claude Code

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.

agentmods
npx agentmods add commands/scenario-labs/skills/squash-message
Clone the repo
git clone --depth 1 https://github.com/scenario-labs/skills

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 squash-message

README.md
[![agentmods](https://agentmods.dev/badge/commands/scenario-labs/skills/squash-message.svg)](https://agentmods.dev/commands/scenario-labs/skills/squash-message)
Your own site
<a href="https://agentmods.dev/commands/scenario-labs/skills/squash-message"><img src="https://agentmods.dev/badge/commands/scenario-labs/skills/squash-message.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 337 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00337
Opus 5 $0.00000 $0.00169
Sonnet 5 $0.00000 $0.00067
Haiku 4.5 $0.00000 $0.00034

Measured 5d ago against content hash 1f29fa73a57e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

squash-message 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 5d 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/squash-message.md · 13 lines

What it actually says

Generate a single squash commit message for the current PR.

  1. Run git fetch origin main --quiet && git log --oneline $(git merge-base HEAD origin/main)..HEAD to see all commits in this branch
  2. Analyze the net diff against main (git diff $(git merge-base HEAD origin/main)..HEAD): what the PR adds, fixes, or refactors relative to main. The commit list is context, not content: the message describes the diff, not the journey.
  3. Write ONE conventional commit message that summarizes the entire PR and passes commitlint.config.js:
    • Title: max 120 chars, conventional commit format (feat/fix/docs/chore), scope from the skill directory names or the cross-cutting scopes (skills, agents, ci, deps, docs, tooling)
    • Body: bullet points of key changes, grouped by category
    • Footer: Co-Authored-By line
  4. Preserve distinct meaningful changes instead of flattening everything into one vague line, but only changes that exist in the net diff. A branch commit that fixes or reworks something introduced earlier in the same branch is development churn: fold it into the item it amends, never list it as a fix. Label a body item feat or fix only when the PR mixes both kinds of net change relative to main; a PR that only adds one thing gets plain bullets describing what landed.
  5. Verify the title passes: echo "TITLE" | pnpm exec commitlint
  6. Copy the message to clipboard with echo "MESSAGE" | pbcopy
  7. Tell me the message you copied
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. 5d ago First seen · 13 lines · 0 tokens per session scan A 1f29fa73a57e

Subscribe to this mod's changes

squash-message is a command published in the GitHub repository scenario-labs/skills (10 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 337 tokens. 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.