Borrowing it
Nothing to install: this file belongs to sanmak/specops. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sanmak/specops/main/.claude/commands/ship-pr.mdgit clone --depth 1 https://github.com/sanmak/specopsWrote 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/sanmak/specops/ship-pr)<a href="https://agentmods.dev/commands/sanmak/specops/ship-pr"><img src="https://agentmods.dev/badge/commands/sanmak/specops/ship-pr/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.
<a href="https://agentmods.dev/commands/sanmak/specops/ship-pr"><img src="https://agentmods.dev/badge/commands/sanmak/specops/ship-pr.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.02264 |
| Opus 5.5 | $0.00000 | $0.00906 |
| Sonnet 5.5 | $0.00000 | $0.00453 |
| Haiku 4.5 | $0.00000 | $0.00226 |
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 1mo 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 — 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 --allto 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):
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.
- 1mo ago First seen · 219 lines · 0 tokens per session scan A a1ba1c1d6cd7
ship-pr is a command published in the GitHub repository sanmak/specops (49 stars, last pushed 2mo 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.
Other commands, from other repositories
skill-creator
Create or update an OpenCode skill using the bundled skill-creator workflow.
skill-registry
Rebuild the OpenCode skill registry for the current project and installed skills.
taskstoissues
A command that turns structured tasks from project design documents into ordered GitHub Issues, written in simplified Chinese.
branch-commit
Return a branch name and concise commit message (max 3 lines) for the current task, grounded in the real git diff; with --apply, create the commit after showing the staged diff. Use when the user only needs quick branch and commit naming before committing, PR packaging is unnecessary, and a real diff exists; use…
approve-proposed
Atomically persist every file marked PROPOSED in the most recent prior assistant turn's ### Artifact changes block, promoting staged content to real files. Invoked on request only. Use when that block contained files marked PROPOSED and you have accepted the inline content of each. Do not use when the prior turn had…
explain
/explain Explain the last agent action (quick mode) /explain --verbose Full trace with file changes and decision rationale /explain --story STORY-XXX All actions for a story in chronological order /explain --agent Last action by a specific agent /explain --session All actions from a specific session /explain --diff…