AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Auto Mr

skill-sgaunet-claude-plugins-auto-mr · by sgaunet

Push current branch, create MR/PR on GitHub, GitLab, or Forgejo, wait for CI pipeline, merge, and clean up branch using auto-mr CLI

No reviews yet
0 installs
31 views
0.0% view→install

Install

$ agentstack add skill-sgaunet-claude-plugins-auto-mr

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-sgaunet-claude-plugins-auto-mr)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
3mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Auto Mr? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

auto-mr Skill

Push the current branch, create a MR/PR on GitHub, GitLab, or Forgejo, wait for the CI pipeline, merge, and clean up the branch — all via the auto-mr CLI.

For git.sylvlab.fr repositories, the underlying auto-mr binary routes via the fgj CLI; GitHub and GitLab remotes are handled automatically as before. Platform detection and routing are handled entirely by the binary — this skill does not branch on the host.

CLI Reference

Flags:
  --labels string             Comma-separated label names (e.g., "bug,enhancement")
  --list-labels               List all available labels and exit
  -l, --log-level string      Set log level (debug, info, warn, error) [default "info"]
  --msg string                Custom message for MR/PR (overrides commit message selection)
  --no-squash                 Disable squash merge (default: squash enabled)
  --pipeline-timeout string   Pipeline/workflow timeout [default "30m"]
  -v, --version               Print version and exit

Workflow

Step 1: Pre-flight Checks

Verify auto-mr is installed:

auto-mr --version

If the command fails, abort with: > auto-mr is not installed. Install it from https://github.com/sgaunet/auto-mr and ensure it is in your PATH.

Get current branch:

git rev-parse --abbrev-ref HEAD

If the branch is main, master, or develop, warn the user: > Warning: you are on a protected branch (`). auto-mr` is intended for feature branches.

Check for uncommitted changes:

git status --porcelain

If the working tree is dirty, warn the user: > Warning: you have uncommitted changes. Consider committing or stashing them before creating a MR/PR.

Step 2: Label Discovery (early exit)

If --list-labels is present in the arguments:

auto-mr --list-labels

Display the output and return. Do not proceed further.

Step 3: Assemble Command

Base command: auto-mr

Append all provided flags verbatim (e.g., --squash, --msg "fix: ...", --labels "bug,help wanted").

If a working_directory context is provided, prefix with cd &&.

Step 4: Confirm Before Executing

Display a summary to the user:

Branch:  
Command: 

Ask the user to confirm via AskUserQuestion: > Proceed with the above command? (yes/no)

If the user declines, abort gracefully.

Step 5: Execute

Run the assembled command. auto-mr handles the full flow:

  1. Push branch to remote
  2. Create MR (GitLab) or PR (GitHub/Forgejo)
  3. Wait for CI pipeline/checks
  4. Merge when CI passes
  5. Delete the remote branch

On success: display the output (includes the MR/PR URL).

On failure: display the error output, then suggest the manual fallback:

git push -u origin 
# Then open a MR/PR via the repository web UI

Working Directory

If a working_directory context is provided (e.g., a worktree path from feature-flow-w), prefix all commands with cd &&. Otherwise, use the current directory.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.