AgentsCommander: Skill for Claude Code

.claude/skills/ship/SKILL.md

ship is a skill for Claude Code from mblua/AgentsCommander. It costs 31 tokens per session (671 once invoked), scanned A, original, MIT.

A guided process for taking a feature branch through committing, pushing, updating from the main branch, merging, and cleaning up.

In plain words
What is it for?
Use it when a feature or bug-fix branch is ready to merge into main.
Why use it?
It keeps the branch-merge steps in order and stops when a step fails or conflicts need attention.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

This is mblua/AgentsCommander's own configuration. It tells Claude Code how to work on AgentsCommander 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 AgentsCommander configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mblua/AgentsCommander. 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/mblua/AgentsCommander/main/.claude/skills/ship/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/mblua/AgentsCommander

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 ship

README.md
[![agentmods](https://agentmods.dev/badge/skills/mblua/agentscommander/ship/github.svg)](https://agentmods.dev/skills/mblua/agentscommander/ship)
Your own site
<a href="https://agentmods.dev/skills/mblua/agentscommander/ship"><img src="https://agentmods.dev/badge/skills/mblua/agentscommander/ship/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 ship

Your own site · 80×15
<a href="https://agentmods.dev/skills/mblua/agentscommander/ship"><img src="https://agentmods.dev/badge/skills/mblua/agentscommander/ship.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 671 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 $0.00031 $0.00671
Opus 5.5 $0.00012 $0.00268
Sonnet 5.5 $0.00006 $0.00134
Haiku 4.5 $0.00003 $0.00067

Measured 2mo ago against content hash 56418d28931d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ship 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.

.claude/skills/ship/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ship Branch to Main

Ship the current branch through the full merge lifecycle. Execute each step in order. If any step fails, STOP and report the issue — do not continue.

Pre-flight

  1. Run rtk git status and rtk git branch --show-current to identify the current branch
  2. If on main, ABORT with: "You are already on main. Switch to a feature branch first."
  3. Show the branch name and ask the user to confirm before proceeding

Step 1 — Commit & Push

  1. Run rtk git status to check for uncommitted changes
  2. If there are changes:
    • Run rtk git diff and rtk git log --oneline -3 to understand context and commit style
    • Stage relevant files (prefer specific files over git add .)
    • Create a commit following the repo's commit message conventions
  3. Push the branch to origin: rtk git push origin <branch>
    • If the remote branch doesn't exist yet, use rtk git push -u origin <branch>

Step 2 — Update from origin/main

  1. Fetch latest: rtk git fetch origin
  2. Check if origin/main has new commits: rtk git log HEAD..origin/main --oneline
  3. If there are new commits, merge: rtk git merge origin/main
  4. If there are merge conflicts:
    • Report the conflicting files
    • STOP and ask the user to resolve them
    • Do NOT continue until the user says conflicts are resolved
  5. If merge brought new commits, push the updated branch: rtk git push origin <branch>

Step 3 — Merge to main

  1. Switch to main: rtk git checkout main
  2. Update local main: rtk git merge origin/main
  3. Merge the branch with: rtk git merge --no-ff <branch>
    • The --no-ff preserves the branch history as a merge commit
  4. Push main to origin: rtk git push origin main

Step 4 — Verify & Cleanup

  1. Verify the merge landed on origin: rtk git log origin/main --oneline -3
    • Confirm the merge commit is visible
    • If NOT visible, STOP and report the issue — do not delete anything
  2. Only after confirming the merge is on origin/main:
    • Delete local branch: rtk git branch -d <branch>
    • Delete remote branch: rtk git push origin --delete <branch>
  3. Final status: rtk git branch -a to confirm cleanup

Read the full file on GitHub · 62 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. 2mo ago First seen · 62 lines · 31 tokens per session scan A 56418d28931d

Subscribe to this mod's changes

ship is a skill published in the GitHub repository mblua/AgentsCommander (12 stars, last pushed today), licensed MIT. It adds 31 tokens to every session and 671 once invoked, about $0.0001 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.