speckit.spex.ship

speckit.spex.ship is a command for Claude Code from rhuss/cc-spex. It costs 22 tokens per session (10,261 once invoked), scanned B, original, Apache-2.0.

A command that runs a software task from written requirements through planning, implementation, review, testing, and verification in one continuous workflow.

In plain words
What is it for?
Use it to carry a feature from its specification to checked code, with configurable levels of human oversight. It is also for reviewing the result and preparing a pull request when the workflow is complete.
Why use it?
It removes the need to manually start each development stage or repeatedly confirm that the next stage should begin. It can also fix issues automatically and optionally create a pull request, a proposed code change for team review.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md). Also seen: reads .claude/ paths; mentions subagents; names the AskUserQuestion tool.

Good fit Use it to carry a feature from its specification to checked code, with configurable levels of human oversight. It is also for reviewing the result and preparing a pull request when the workflow is complete.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/rhuss/cc-spex/speckit.spex.ship
Install

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.

Clone the repo
git clone --depth 1 https://github.com/rhuss/cc-spex

Made for: Claude Code.

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 speckit.spex.ship

README.md
[![agentmods](https://agentmods.dev/badge/commands/rhuss/cc-spex/speckit.spex.ship.svg)](https://agentmods.dev/commands/rhuss/cc-spex/speckit.spex.ship)
Your own site
<a href="https://agentmods.dev/commands/rhuss/cc-spex/speckit.spex.ship"><img src="https://agentmods.dev/badge/commands/rhuss/cc-spex/speckit.spex.ship.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 10,261 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00022 $0.10261
Opus 5 $0.00011 $0.05130
Sonnet 5 $0.00004 $0.02052
Haiku 4.5 $0.00002 $0.01026

Measured 8d ago against content hash 5c606e11a215, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

speckit.spex.ship scanned grade B with 1 finding 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

DIRTY=$(git status --porcelain 2>/dev/null | grep -v -E '^.{2} \.claude/(commands/speckit\.|settings)' | grep -v -E '^.{2} \.specify/(extensions/|\.spex-)' || true)
specs/038-neutral-command-vocab/pre-rewrite-snapshot/spex/commands/speckit.spex.ship.md · 968 lines

How it starts

The opening of the file, as written. The whole thing — 968 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Autonomous Full-Cycle Workflow (speckit-spex-ship)

CONTINUOUS EXECUTION RULE (READ THIS FIRST)

This pipeline runs ALL stages without stopping. After completing any stage, you MUST immediately begin the next stage. There are no natural stopping points between stages.

  • Do NOT say "Ready for the next stage" and wait.
  • Do NOT say "Shall I proceed?" and wait.
  • Do NOT say "Proceeding to..." and wait.
  • Do NOT treat a stage completion as a task completion.
  • Do NOT output a summary and stop.

The pipeline is ONE continuous task. It starts at the first stage and runs through the last stage. The ONLY reasons to pause are:

  1. ask is always AND a review stage has findings requiring user input.
  2. A blocker error occurs (test failure, syntax error, security issue).
  3. Stage 7 (review-code) completes: the pipeline is done and presents a completion prompt for the user to decide how to proceed (submit PR, merge directly, or stop).

After every stage: update the state file, then immediately start the next stage. No waiting, no confirmation, no stopping.

Overview

This skill chains the entire spex workflow autonomously: specify, clarify, review-spec, plan, review-plan, tasks, implement, deep-review, and verify. Point it at a brainstorm document and choose an oversight level to control how much human oversight the pipeline requires.

This skill requires both spex-gates and spex-deep-review extensions to be enabled.

Prerequisites

Extension Validation

Check that required extensions are enabled:

# Check for enabled extensions
GATES=$(specify extension list 2>/dev/null | grep -c 'spex-gates.*enabled' || echo 0)
DEEP_REVIEW=$(specify extension list 2>/dev/null | grep -c 'spex-deep-review.*enabled' || echo 0)

if [ "$GATES" = "0" ] || [ "$DEEP_REVIEW" = "0" ]; then
  echo "ERROR: speckit-spex-ship requires both spex-gates and spex-deep-review extensions."
  echo ""
  echo "Enable them with:"
  echo "  specify extension enable spex-gates && specify extension enable spex-deep-review"
  echo ""
  echo "Missing extensions:"
  [ "$GATES" = "0" ] && echo "  - spex-gates"
  [ "$DEEP_REVIEW" = "0" ] && echo "  - spex-deep-review"
fi

Read the full file on GitHub · 968 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. 8d ago First seen · 968 lines · 22 tokens per session scan B 5c606e11a215

Subscribe to this mod's changes

speckit.spex.ship is a command published in the GitHub repository rhuss/cc-spex (115 stars, last pushed 19d ago), licensed Apache-2.0. It adds 22 tokens to every session and 10,261 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.