ship-pr

A command workflow that commits current changes on a new Git branch, pushes that branch, and opens a pull request. A pull request is a request for others to review and merge code.

In plain words
What is it for?
Use it when your changes are ready to send for review, including checking the worktree, creating a branch, committing safe files, pushing to the remote repository, and opening a pull request.
Why use it?
It packages local work for review while leaving the original branch unchanged. It also checks for sensitive files before staging changes.

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/sanmak/specops/ship-pr
Clone the repo
git clone --depth 1 https://github.com/sanmak/specops

Made for: Claude Code.

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 2,264 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 $0.00000 $0.02264
Opus 5 $0.00000 $0.01132
Sonnet 5 $0.00000 $0.00453
Haiku 4.5 $0.00000 $0.00226

Measured 2d ago against content hash a1ba1c1d6cd7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ship-pr 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 2d 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/ship-pr.md · 219 lines

How it starts

The opening of the file, as written. The whole thing — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Commit all changes to a new branch, push, and open a PR for review. The original branch stays clean.

Instructions

This command performs a commit → branch → push → PR workflow. Follow these steps precisely. Do NOT add a Co-Authored-By line to the commit.


Step 0: Record the original branch

Run git rev-parse --abbrev-ref HEAD and save the result as ORIGINAL_BRANCH.

Set TARGET_BRANCH = ORIGINAL_BRANCH.

(The PR will always target the branch the user was on when they ran this command.)


Part 1: Commit

Step 1: Check for changes

Run git status to see the current state. If there are no modified, new, or deleted files (working tree is clean AND no staged changes), inform the user "Nothing to ship" and STOP.

Step 2: Identify sensitive files

Before staging, check if any of these patterns appear in the untracked or modified files:

  • .env, .env.*
  • credentials.json, secrets.json, *.pem, *.key
  • Any file with "secret", "credential", or "token" in its name
  • id_rsa, id_ed25519, or any SSH private key files

If any are found, list them with a WARNING and do NOT stage them. Proceed with staging all other files.

Step 3: Auto-stage files

Run git add -A to stage all changes (this respects .gitignore automatically).

Then un-stage any sensitive files identified in Step 2 using git reset HEAD <file> for each one.

Step 4: Check for source/generated file consistency

Examine the staged files list with git diff --cached --name-only.

If any files under core/, generator/templates/, generator/generate.py, or platforms/*/platform.json are staged:

  • Run python3 generator/generate.py --all to regenerate platform outputs
  • Stage the regenerated files: git add platforms/ skills/ .claude-plugin/

If any of these checksummed files are staged (skills/specops/SKILL.md, schema.json, platforms/claude/SKILL.md, platforms/claude/platform.json, platforms/cursor/specops.mdc, platforms/cursor/platform.json, platforms/codex/SKILL.md, platforms/codex/platform.json, platforms/copilot/specops.instructions.md, platforms/copilot/platform.json, core/workflow.md, core/safety.md, hooks/pre-commit, hooks/pre-push, scripts/install-hooks.sh, .claude-plugin/plugin.json, .claude-plugin/marketplace.json):

Read the full file on GitHub · 219 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. 2d ago First seen · 219 lines · 0 tokens per session scan A a1ba1c1d6cd7

Subscribe to this mod's changes

ship-pr is a command published in the GitHub repository sanmak/specops (49 stars, last pushed 29d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,264 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 2026-08-30.