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.
git clone --depth 1 https://github.com/rhuss/cc-spexWrote 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/commands/rhuss/cc-spex/speckit.spex.ship)<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>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 | $0.00022 | $0.10261 |
| Opus 5 | $0.00011 | $0.05130 |
| Sonnet 5 | $0.00004 | $0.02052 |
| Haiku 4.5 | $0.00002 | $0.01026 |
Grade B, and why
speckit.spex.ship scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
DIRTY=$(git status --porcelain 2>/dev/null | grep -v -E '^.{2} \.claude/(commands/speckit\.|settings)' | grep -v -E '^.{2} \.specify/(extensions/|\.spex-)' || true) 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:
askisalwaysAND a review stage has findings requiring user input.- A blocker error occurs (test failure, syntax error, security issue).
- 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
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 · 968 lines · 22 tokens per session scan B 5c606e11a215
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.
Other commands, from other repositories
commit
A command that examines staged Git changes and proposes a commit message using the Conventional Commits format, such as feat, fix, or docs. Git is a tool for tracking changes to code.
release-notes
Generate consistent, well-structured release notes from git history. Triggered on release tags following semver patterns (v..) to produce categorized changelog with breaking changes, features, fixes, and contributor attribution.
doctor
Diagnosticar y reparar problemas del framework Don Cheli, git y entorno. Usa cuando el usuario dice "doctor", "problemas del framework", "don cheli no funciona", "repair Don Cheli", "debug setup", "setup broken", "framework broken", "reparar entorno". Detecta y repara issues de configuración, git y dependencias…
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
handoff
Export a Waybill Bundle by default, or import one when requested.
release-plan
A release-planning command for a software change. It documents the release scope, rollback plan, gradual or full rollout, and monitoring before waiting for human approval.