Claude Code Agent Development
anthropics/claude-plugins-official
Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.
Verify local CI passes before pushing or opening a PR. An agent skill from pulp-platform/snitch_cluster.
Install Ship
$ npx skills add pulp-platform/snitch_cluster --skill ship -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install pulp-platform/snitch_cluster ship --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/pulp-platform/snitch_cluster.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/ship .claude/skills/ship && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "ship" agent skill from https://github.com/pulp-platform/snitch_cluster/tree/main/.claude/skills/ship into .claude/skills/ship/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ship", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/pulp-platform/snitch_cluster/tree/main/.claude/skills/shipType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add pulp-platform/snitch_cluster --skill ship -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install pulp-platform/snitch_cluster ship --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pulp-platform/snitch_cluster.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/ship .agents/skills/ship && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "ship" agent skill from https://github.com/pulp-platform/snitch_cluster/tree/main/.claude/skills/ship into .agents/skills/ship/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ship", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add pulp-platform/snitch_cluster --skill ship -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install pulp-platform/snitch_cluster ship --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pulp-platform/snitch_cluster.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/ship .cursor/skills/ship && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "ship" agent skill from https://github.com/pulp-platform/snitch_cluster/tree/main/.claude/skills/ship into .cursor/skills/ship/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ship", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/pulp-platform/snitch_cluster.git --path .claude/skills/ship--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add pulp-platform/snitch_cluster --skill ship -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install pulp-platform/snitch_cluster ship --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pulp-platform/snitch_cluster.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/ship .gemini/skills/ship && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "ship" agent skill from https://github.com/pulp-platform/snitch_cluster/tree/main/.claude/skills/ship into .gemini/skills/ship/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ship", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install pulp-platform/snitch_cluster shipInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add pulp-platform/snitch_cluster --skill ship -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/pulp-platform/snitch_cluster.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/ship .github/skills/ship && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "ship" agent skill from https://github.com/pulp-platform/snitch_cluster/tree/main/.claude/skills/ship into .github/skills/ship/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ship", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add pulp-platform/snitch_cluster --skill ship -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install pulp-platform/snitch_cluster ship --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pulp-platform/snitch_cluster.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/ship .opencode/skills/ship && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "ship" agent skill from https://github.com/pulp-platform/snitch_cluster/tree/main/.claude/skills/ship into .opencode/skills/ship/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ship", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
ship- GitHub stars
- 151
- Token cost
- ~537 tokens
- SKILL.md length
- 300 words
- Files
- 1
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Verify local CI passes before pushing or opening a PR. An agent skill from pulp-platform/snitch_cluster.
- Works in 3 steps: Delegate. Ask the ci-runner subagent to… → Iterate on real failures. ci-runner… → Push. Once ci-runner reports green, the…
- Tasks that involve Subagents
- SKILL.md covers Why this exists, The loop, If the hook still blocks after… and Limitations, honestly
- Calls make, git and gh
What it does
Ship is an agent skill from pulp-platform/snitch_cluster. Verify local CI passes before pushing or opening a PR. Use this whenever a feature is implementation-complete and about to be pushed — it delegates verification to the ci-runner subagent and only pushes once it reports a receipt-writing make ci has succeeded against the current tree.
Its SKILL.md is about 540 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows, covering Subagents. The repository describes itself as: An energy-efficient RISC-V floating-point compute cluster. The licence is Apache-2.0.
When your agent uses it
- Tasks that involve Subagents
Example prompts
- “/ship”
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- Delegate. Ask the ci-runner subagent to verify the tree is ready to
- Iterate on real failures. ci-runner reports only a real failure or a
- Push. Once ci-runner reports green, the receipt is written and
What it can do on your machine
Read from SKILL.md and the folder at commit 8142c0f. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
makegitgh
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git and gh, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Ship loads about 537 tokens when it runs. Until then it costs about 73 tokens; SKILL.md has 300 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from pulp-platform/snitch_cluster at commit 8142c0f, republished under its Apache-2.0 licence (© pulp-platform). 300 words, ~537 tokens.
Download SKILL.mdSave it as
.claude/skills/ship/SKILL.md (or your agent's skills folder).- name
- ship
- description
- Verify local CI passes before pushing or opening a PR. Use this whenever a feature is implementation-complete and about to be pushed — it delegates verification to the ci-runner subagent and only pushes once it reports a receipt-writing `make ci` has succeeded against the current tree.
This repo enforces that git push and gh pr create are blocked
until a successful make ci run has stamped a receipt for the exact
current working tree. This skill is the procedure to get there.
Why this exists
A green make ci is a genuine local stand-in for "would GitHub + GitLab CI
pass".
The receipt is a fingerprint of the tree (HEAD + diff + untracked files), touching anything invalidates it, so this must be the last step before pushing, not a one-time box to tick.
The loop
Delegate. Ask the
ci-runnersubagent to verify the tree is ready to push. Don't run CI yourself — its logs are too large for this context, and how it gets there (a fast lane before the full suite) is its own concern, not something to manage from here.Iterate on real failures.
ci-runnerreports only a real failure or a fully greenmake ci— never an intermediate pass. Fix what it reports and re-invoke it.Push. Once
ci-runnerreports green, the receipt is written and current —git push(orgh pr create) will no longer be blocked. Don't re-run any other check first; the receipt check is exact.
If the hook still blocks after a green run
The fingerprint is sensitive to any tree change, including ones made after
make ci finished — e.g. a last commit message edit that touches no tracked
content still updates HEAD, or a stray file created afterwards. If this
happens, that's the fingerprint correctly doing its job: re-run make ci
(via ci-runner) rather than trying to work around the block.
Limitations, honestly
- The receipt check is not cryptographic proof that CI actually ran — it's a file comparison, and defends against forgetting this step, not against deliberately fabricating a receipt. Don't do that; run the real thing.
© pulp-platform, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .claude/skills/ship of pulp-platform/snitch_cluster.
Open the folder on GitHubat commit 8142c0f
Compare with similar skills
Ship next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Ship this skillpulp-platform/snitch_cluster | 151 | — | ~537 | Automated safety check: Pass | Apache-2.0 | |
| Claude Code Agent Developmentanthropics/claude-plugins-official | 38k | 8 repos | ~2.8k | Automated safety check: Pass | Apache-2.0 | |
| Subagent Driven DevelopmentAsvarox/allkaraoke | 261 | 38 repos | ~1.2k | Automated safety check: Pass | None | |
| Dispatching Parallel Agentsultralisp/ultralisp | 258 | 41 repos | ~1.5k | Automated safety check: Pass | None | |
| Paseo Advisor Second Opiniongetpaseo/paseo | 20k | 1 repos | ~756 | Automated safety check: Pass | Custom licence | |
| Task Observerrebelytics/one-skill-to-rule-them-all | 3.2k | 1 repos | ~12k | Automated safety check: Pass | CC-BY-4.0 |
Similar skills
- Official
Subagent Driven Development
Asvarox/allkaraoke
A skill your agent uses when executing implementation plans with independent tasks in the current session
Dispatching Parallel Agents
ultralisp/ultralisp
A skill your agent uses when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Paseo Advisor Second Opinion
getpaseo/paseo
Launches one separate agent through Paseo to give a second opinion on the current task, with a self-contained briefing and no permission to edit files.
Task Observer
rebelytics/one-skill-to-rule-them-all
Monitors task execution for skill improvement opportunities.
O2 Review Loop
openobserve/openobserve
Splits a change into planner, coder and independent reviewer roles: you confirm a spec, a subagent implements it, and a separate reviewer checks each round's local WIP commit.
Related
Categories
Questions about Ship
What does Ship do?
Verify local CI passes before pushing or opening a PR. An agent skill from pulp-platform/snitch_cluster. Ship is an agent skill from pulp-platform/snitch_cluster. Verify local CI passes before pushing or opening a PR.
When should I use Ship?
Ship fits situations like: tasks that involve Subagents.
How do I install Ship in Claude Code?
Run `npx skills add pulp-platform/snitch_cluster --skill ship -a claude-code`. Or copy the skill folder (.claude/skills/ship in pulp-platform/snitch_cluster) into .claude/skills/ship in your project. Claude Code loads it when a task matches its description.
How do I install Ship in Codex?
Run `npx skills add pulp-platform/snitch_cluster --skill ship -a codex`. Or copy the skill folder (.claude/skills/ship in pulp-platform/snitch_cluster) into .agents/skills/ship in your project. Codex loads it when a task matches its description.
Can I use Ship in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add pulp-platform/snitch_cluster --skill ship -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ship, .gemini/skills/ship, .github/skills/ship and .opencode/skills/ship in your project.
What does Ship need to run?
Going by SKILL.md and its folder, Ship needs the command-line tools its instructions call (make, git and gh).
Does Ship access the network?
SKILL.md contains no URLs. Its commands use git and gh, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Ship safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Ship use?
Ship is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Ship use?
About 537 tokens (SKILL.md is roughly 2.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Ship?
Skills that share tags, products or a category with Ship: Claude Code Agent Development (anthropics/claude-plugins-official, 38k stars), Subagent Driven Development (Asvarox/allkaraoke, 261 stars), Dispatching Parallel Agents (ultralisp/ultralisp, 258 stars) and Paseo Advisor Second Opinion (getpaseo/paseo, 20k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Ship?
pulp-platform (a GitHub organization) maintains it in pulp-platform/snitch_cluster, which has 151 GitHub stars. The repository was last updated on October 2, 2026.
Source: pulp-platform/snitch_cluster on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.