mr-submit

mr-submit is a skill for Claude Code from Jarroslav/agentic-os. It costs 159 tokens per session (2,277 once invoked), scanned A, original, Apache-2.0.

A controlled Git workflow for committing changes, pushing them, and opening a merge request or pull request. A merge request or pull request is a proposed code change sent for review before it is merged.

In plain words
What is it for?
Use it when you explicitly need to commit, push, or open a review request, using the project’s workflow rules and its configured review-system adapter.
Why use it?
It makes the required ticket references, branch names, commit format, and review-platform details explicit. It also prevents review requests from being created without a direct request.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the agentic-sdlc plugin — 27 skills, 5 agents shipped together

Good fit Use it when you explicitly need to commit, push, or open a review request, using the project’s workflow rules and its configured review-system adapter.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jarroslav/agentic-os/mr-submit
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.

Any agent
npx skills add Jarroslav/agentic-os --skill mr-submit
Clone the repo
git clone --depth 1 https://github.com/Jarroslav/agentic-os

Made for: Claude Code.

Or install agentic-sdlc, the plugin that ships this one along with the rest of its 27 skills, 5 agents.

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 mr-submit

README.md
[![agentmods](https://agentmods.dev/badge/skills/jarroslav/agentic-os/mr-submit/github.svg)](https://agentmods.dev/skills/jarroslav/agentic-os/mr-submit)
Your own site
<a href="https://agentmods.dev/skills/jarroslav/agentic-os/mr-submit"><img src="https://agentmods.dev/badge/skills/jarroslav/agentic-os/mr-submit/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 mr-submit

Your own site · 80×15
<a href="https://agentmods.dev/skills/jarroslav/agentic-os/mr-submit"><img src="https://agentmods.dev/badge/skills/jarroslav/agentic-os/mr-submit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 159 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,277 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 $0.00159 $0.02277
Opus 5.5 $0.00064 $0.00911
Sonnet 5.5 $0.00032 $0.00455
Haiku 4.5 $0.00016 $0.00228

Measured 2mo ago against content hash a5ed2894aad4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mr-submit 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 2mo 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.

plugins/agentic-sdlc/skills/mr-submit/SKILL.md · 260 lines

How it starts

The opening of the file, as written. The whole thing — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Commit, Push, and Open MR/PR

Blast radius R3 — the create step reaches an external service. Treat MR/PR creation as gated: it fires only on a direct user request, never as a side effect of another skill.

This skill hardcodes no VCS platform. Commit and branch shapes come from the git-workflow guide; the create/check mechanism comes from a runtime adapter declared in the project guide. Everything platform-specific is resolved, not assumed.

When this runs

Trigger only on an explicit user ask to commit, push, or open a review request. sdlc-auto does not call this skill on its own — the autonomous pipeline never self-triggers commit/push/MR side effects.

Route by request:

User says Do
"commit changes" Commit only (ticket required)
"push changes" Push only
"create MR" / "open a PR" Full push + create workflow

Inputs

Source Provides
.agentic/guides/standards/git-workflow.md Commit pattern, branch pattern, MR title format
.agentic/guides/project.md → ## Review Adapter Adapter status, adapter handle, instructions, body template
references/mr-adapters.md Adapter contract + sample configs (check/create operations, auth notes, no-adapter fallback)
Conversation context Ticket reference, user request type

Outputs

  • A commit whose message begins with a validated ticket reference.
  • A pushed branch tracking origin.
  • A created MR/PR (URL surfaced to the user), unless one already exists.
  • A run-journal entry at .agentic/runs/<branch>.json.
  • A user-gated handoff suggestion to mr-watch (never auto-invoked).

Step 0 — Load conventions and resolve the adapter

Read .agentic/guides/standards/git-workflow.md. If it is not present, stop immediately and emit this marker verbatim:

[GUIDE MISSING] `.agentic/guides/standards/git-workflow.md` not found.
Run the `repo-guides` skill to generate project guides before using `mr-submit`.

repo-guides is a hard upstream dependency — without the guide there is no convention to enforce, so do not fall through to defaults.

Read the full file on GitHub · 260 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2mo ago First seen · 260 lines · 159 tokens per session scan A a5ed2894aad4

Subscribe to this mod's changes

mr-submit is a skill published in the GitHub repository Jarroslav/agentic-os (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 159 tokens to every session and 2,277 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-08-31.