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.
npx skills add felipearomani/claude-shipyard --skill open-prgit clone --depth 1 https://github.com/felipearomani/claude-shipyardWrote 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/skills/felipearomani/claude-shipyard/open-pr)<a href="https://agentmods.dev/skills/felipearomani/claude-shipyard/open-pr"><img src="https://agentmods.dev/badge/skills/felipearomani/claude-shipyard/open-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/skills/felipearomani/claude-shipyard/open-pr"><img src="https://agentmods.dev/badge/skills/felipearomani/claude-shipyard/open-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 | $0.00168 | $0.02895 |
| Opus 5 | $0.00084 | $0.01448 |
| Sonnet 5 | $0.00034 | $0.00579 |
| Haiku 4.5 | $0.00017 | $0.00290 |
Grade A, and why
open-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 8d 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 — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.
open-pr
Wrap a feature branch and open a pull request. Single-shot workflow: rebase → lint → commit → push → PR.
You are operating autonomously once invoked. No confirmation prompts before push or PR creation. The only stop condition is a git conflict during rebase.
When NOT to run
Refuse and ask the user to clarify if any of these hold:
- The current branch IS the base branch (
main,master) — there is nothing to PR. - The repo has no GitHub remote (
gh repo viewfails) — a PR cannot be opened. - The
ghCLI is not authenticated (gh auth statusfails) — authenticate first. - The working tree has a destructive operation in progress (
.git/MERGE_HEAD,.git/CHERRY_PICK_HEAD, an ongoing rebase) — finish or abort that first.
If none of those hold, proceed.
The workflow
Six phases. Do not skip. Track them so progress is visible to the user.
1. Preflight — capture state, detect the base branch
2. Sync — rebase onto origin/<base>; halt on conflict
3. Lint — auto-detect and run the linter/formatter
4. Commit — Conventional Commits message over the diff
5. Push — force-with-lease (a rebase rewrites history)
6. PR — gh pr create + share the URL
Phase 1 — Preflight
Run these, capture the output:
git rev-parse --abbrev-ref HEAD # current branch
git status --porcelain # dirty state
git rev-parse --git-dir # git dir (worktree-safe)
gh auth status # gh ready?
git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null # default branch
Determine the base branch in this order:
git symbolic-ref refs/remotes/origin/HEAD→ striprefs/remotes/origin/→ use it.- If that fails:
git ls-remote --symref origin HEAD | awk '/^ref:/ {print $2}'→ striprefs/heads/. - If still unknown: try
mainthenmasterviagit ls-remote --heads origin <name>. - If none resolve: refuse — the repo has no clear default.
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.
- 8d ago First seen · 296 lines · 168 tokens per session scan A 04365dbae612
open-pr is a skill published in the GitHub repository felipearomani/claude-shipyard (1 stars, last pushed 8d ago), licensed MIT. It adds 168 tokens to every session and 2,895 once invoked, about $0.0008 per session on Opus 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.
Other skills, from other repositories
pr-watch
Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.
deploy-steward
Mainline deploy steward. Consumes ready PRs, owns a lease on mainline landing, refreshes PR state, updates stale branches, waits for CI and deploy gates, merges or queues one candidate at a time, and opens repair tasks for failures.
merge-review
Reviews pending fleet worktree merges before they're accepted. Reads the merge-check queue, detects file-level conflicts between branches, proposes a safe merge order, and surfaces reconciliation plans for overlapping changes.
bump-sdk-version
Bump the FutureSearch SDK version across all files. Use when releasing a new SDK version, updating version numbers, or the user says bump version, release, version bump.
pr-feedback
Work a reviewer's comments on a pull request to the end - all three comment surfaces enumerated before any is triaged, every comment fixed, declined with a reason, or ticketed, push before you reply. Use when a PR comes back with review feedback or a red check.
dos-verify-done-claims
Before accepting an agent's 'done / shipped / fixed' claim, verify it against ground truth (git ancestry + the commit's own diff) using the DOS kernel's dos verify and dos commit-audit — never the agent's own narration.