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.
npx agentmods add commands/leanandmean/mach10/pr-mergegit clone --depth 1 https://github.com/LeanAndMean/mach10Wrote 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.
[](https://agentmods.dev/commands/leanandmean/mach10/pr-merge)<a href="https://agentmods.dev/commands/leanandmean/mach10/pr-merge"><img src="https://agentmods.dev/badge/commands/leanandmean/mach10/pr-merge.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00014 | $0.01120 |
| Opus 5 | $0.00007 | $0.00560 |
| Sonnet 5 | $0.00003 | $0.00224 |
| Haiku 4.5 | $0.00001 | $0.00112 |
Grade A, and why
pr-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 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.
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Merge and Release
You are merging a PR that has passed review and the pre-merge checklist, then optionally creating a release.
User input: $ARGUMENTS
Step 1: Parse Input
The user's input contains:
- A PR number (required)
- Additional context or constraints (optional)
Extract the PR number from the input. If the input is ambiguous, ask the user to clarify. If context was provided, note it for use in later steps (e.g., release notes guidance, version tag preference).
Step 2: Verify Readiness
Confirm the PR is ready to merge:
gh pr view <pr-number> --json state,mergeable,mergeStateStatus,reviewDecision,statusCheckRollup
If there are blocking issues, report them to the user and stop. Do NOT force-merge.
- Failed CI checks: Suggest
/clearthen/mach10:pr-ci-fix <pr-number>to diagnose and fix the failures. - Merge conflicts: Suggest resolving conflicts manually or rebasing the branch.
- Missing review approval: Suggest requesting a review.
- Branch behind main: When
mergeStateStatusisBEHIND, suggest/clearthen/mach10:pr-pre-merge <pr-number>to update the branch before merging.
Step 3: Merge
Merge the PR using the repository's default merge strategy, and delete the remote feature branch in the same command:
gh pr merge <pr-number> --delete-branch
Then update local main:
git checkout main && git pull
Clean up the local feature branch if it still exists. Get the branch name from the PR:
gh pr view <pr-number> --json headRefName --jq .headRefName
Then delete the local branch:
git branch -d <branch-name-from-above>
Step 4: Ask About Release
If the user provided context about release creation, honor it as guidance for this step:
- Skip directives (e.g., "skip release", "no release this time"): Skip the
AskUserQuestionbelow entirely and proceed directly to Step 6. Report in CLI output: "Skipping release per user request." The user has already declined; re-asking is friction without safety benefit. No release will be created; this is the safe path. - Release-creating directives (e.g., "tag as v2.0.0", "highlight the auth changes"): Still ask the question below, but frame it to acknowledge the user wants to create a release and present "Create release" as the recommended choice in the question text. Stash the specific details (tag, highlights, notes style) for the Step 5 draft. The yes/no gate is preserved because a release is a substantive action -- Claude should not draft and create one without an explicit confirmation, even if the user named a tag.
- No release-relevant context: Ask the question below as a neutral yes/no.
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.
- 5d ago First seen · 121 lines · 14 tokens per session scan A aaf045d80f78
pr-merge is a command published in the GitHub repository LeanAndMean/mach10 (20 stars, last pushed 3mo ago), licensed MIT. It adds 14 tokens to every session and 1,120 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.
Other commands, from other repositories
release
Release manager for frontend and mobile. Writes App Store notes, user-facing changelog, flags stale docs and landing copy. Actions: notes | changelog | docs | sync.
deploy
Start Phase 6 — propose a deployment for human approval and, once approved, execute with post-deploy verification.
doctor
Health check for greatcto. Shows pipeline state, missing artefacts, hook status, last run per agent, and permission-denied tail.
review
12-angle code review + skeptical triage (3-round + arbiter) for security/reliability P0/P1 findings, OR traceability tree. Default: review current branch vs main. --deep: triage ALL P0/P1 angles (not just security). With trace : render REQ → IMPL → TEST tree for impact analysis. Creates or closes gate:code for…
discover
Run a full product discovery cycle — from outcome definition through opportunity mapping, prioritisation, and experiment design. Use when the team isn't sure what to build next, or before writing a PRD for a complex feature space.
resume
Resume a previous session. Reads recent session logs, open tasks, and last decisions — gives Claude full context without re-explaining the project.