Borrowing it
Nothing to install: this file belongs to lensapp/lens-sandbox. 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/lensapp/lens-sandbox/main/.claude/skills/ship/SKILL.mdgit clone --depth 1 https://github.com/lensapp/lens-sandboxWrote 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/lensapp/lens-sandbox/ship)<a href="https://agentmods.dev/skills/lensapp/lens-sandbox/ship"><img src="https://agentmods.dev/badge/skills/lensapp/lens-sandbox/ship.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00058 | $0.01910 |
| Opus 5 | $0.00029 | $0.00955 |
| Sonnet 5 | $0.00012 | $0.00382 |
| Haiku 4.5 | $0.00006 | $0.00191 |
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 3d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ship — pipeline dispatcher
You contain zero domain logic. Your only job is: figure out where the work stands, invoke the right sub-skill via the Skill tool, and keep going until the next human gate or until the pipeline is done. The sub-skills own all behavior and all human checkpoints — you inherit their pauses, you never add shortcuts around them.
One invocation does as much as the next human gate allows. Across a large
effort the user runs /ship many times; each time you resume from observable
state, never from conversation memory.
Arguments
- (empty) — detect phase from the current branch and plan file.
- Issue number /
#124/ issue URL — read it (gh issue view <n>) and use its content as the problem seed for planning. - Free text — a new idea; start at planning with it as the problem seed.
Isolated worktree
Do NOT run the pipeline in the user's working directory — they may be in the
middle of something else, and /ship can start from a one-line idea while
they sit on main. When the Spec + plan phase creates the feature branch,
create a worktree for it (same pattern as /code-review):
MAIN_ROOT="$(git worktree list | head -1 | awk '{print $1}')"
SHIP_DIR="$MAIN_ROOT/.ship/<branch>"
mkdir -p "$MAIN_ROOT/.ship"
git worktree add "$SHIP_DIR" -b <branch> origin/main
Ensure .ship/ is listed in .git/info/exclude. Every subsequent phase —
implementation, /green, make e2e, /code-review, /create-pr — runs
inside $SHIP_DIR. On resume, if the plan file names a branch whose worktree
is missing, re-add it (git worktree add "$SHIP_DIR" <branch>).
The worktree builds its own target/ — real disk on this host. /green's
disk guard applies per-worktree.
Cleanup happens on PR terminal state, not at first "everything ticked" —
an open PR can still receive review comments, and the Respond phase needs the
worktree. When the Done row runs, check gh pr view --json state:
MERGEDorCLOSED→git worktree remove "$SHIP_DIR"(reclaims itstarget/),git branch -d <branch>, delete the plan file, andgit worktree prune.OPEN→ keep everything; report "awaiting review/merge — rerun /ship after merge to clean up".- No PR / no GitHub → there is no merge event to observe; ask the user before removing anything.
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.
- 3d ago Changed · +5 lines · -3 tokens per session 644cd525c528
- 8d ago First seen · 127 lines · 61 tokens per session scan A dce6b42d8c8f
ship is a skill published in the GitHub repository lensapp/lens-sandbox (10 stars, last pushed yesterday), licensed Apache-2.0. It adds 58 tokens to every session and 1,910 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…