ship

ship is a command for Claude Code from openplanr/planr-pipeline. It costs 28 tokens per session (7,616 once invoked), scanned A, original, MIT.

A command that runs the development phase of a feature pipeline, coordinating coding, quality checks, infrastructure, documentation, and a project snapshot.

In plain words
What is it for?
Use it to develop one or more planned tasks, run frontend and backend agents, perform QA, optionally generate DevOps and documentation work, and refresh CLAUDE.md.
Why use it?
It organizes the work after planning and includes checks before the feature is treated as ready, while requiring human review before it is chained from planning.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions CLAUDE.md; mentions subagents; names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the planr-pipeline plugin — 8 skills, 10 commands, 9 agents, 1 hook shipped together

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add openplanr/planr-pipeline
Claude Code
/plugin install planr-pipeline

Made for: Claude Code.

Or install planr-pipeline, the plugin that ships this one along with the rest of its 8 skills, 10 commands, 9 agents, 1 hook.

Wrote 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.

agentmods badge for ship

README.md
[![agentmods](https://agentmods.dev/badge/commands/openplanr/planr-pipeline/ship.svg)](https://agentmods.dev/commands/openplanr/planr-pipeline/ship)
Your own site
<a href="https://agentmods.dev/commands/openplanr/planr-pipeline/ship"><img src="https://agentmods.dev/badge/commands/openplanr/planr-pipeline/ship.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 7,616 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 5.1 $0.00028 $0.07616
Opus 5 $0.00014 $0.03808
Sonnet 5 $0.00006 $0.01523
Haiku 4.5 $0.00003 $0.00762

Measured 6d ago against content hash ec49ca74173c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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 6d 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.

commands/ship.md · 384 lines

How it starts

The opening of the file, as written. The whole thing — 384 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/planr-pipeline:ship {slug …}

Orchestrates the DEV Phase for feat-${SLUG} (see procedures/ship-arguments-and-cost-gate.md for flag stripping rules). Generates production code from PO-Phase task files, runs the qa-agent gate, optionally generates infra and docs, then refreshes CLAUDE.md via the snapshot skill.

Flags:

Flag Behaviour
--task T-NNN Run DEV + QA/doc stages only for id: T-NNN frontmatter (validated post mode-detection). Forces single-task.
--yes Skip the COST ESTIMATE interactive gate (still prints the labelled estimate block once); implies dispatch style native.
--no-devops, --no-docs Step 4 opt-outs unchanged.
--workflow / --native Pre-select the Claude Code multi-task dispatch style (host-scheduled DAG vs free native fan-out); skips the B.3 style prompt. Ignored on cursor/codex/unknown.
--all-tasks Force multi-task on a host that can run parallel subagents.

Fatal errors obey fatal-error-format.md.

Per ${CLAUDE_PLUGIN_ROOT}/docs/rules.md R1, this command MUST NOT be auto-chained from /planr-pipeline:plan. A human review step is mandatory between PO Phase and DEV Phase.


Step 0 — Write snapshot sentinel

Touch .claude/.snapshot-pending so the Stop hook (in ${CLAUDE_PLUGIN_ROOT}/hooks/hooks.json) fires a reminder if this command aborts before reaching Step 5.


Step 0.5 — Parse argv (ship-arguments-and-cost-gate.md Phase A)

Execute ${CLAUDE_PLUGIN_ROOT}/procedures/ship-arguments-and-cost-gate.md → Phase A only before anything that needs ${SLUG}.


Step 1 — Mode detection + input validation

1a — Detect planr spec mode

Run procedure: ${CLAUDE_PLUGIN_ROOT}/procedures/mode-detection.md using ${SLUG} as the slug input variable (equivalent historically to stripping feature token from $ARGUMENTS). After it executes, MODE and (for spec-driven mode) SPEC_DIR / FEAT_DIR are bound. The procedure also handles the self-heal-on-missing-stack.md pathway and the path-resolution table.

Read the full file on GitHub · 384 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. 6d ago First seen · 384 lines · 28 tokens per session scan A ec49ca74173c

Subscribe to this mod's changes

ship is a command published in the GitHub repository openplanr/planr-pipeline (2 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 7,616 once invoked, about $0.0001 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.

Related

Other commands, from other repositories