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.
npx agentmods add commands/shipwithai/shipwithai-plugins/setupgit clone --depth 1 https://github.com/ShipWithAI/shipwithai-pluginsWhat 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 | $0.00025 | $0.04382 |
| Opus 5 | $0.00013 | $0.02191 |
| Sonnet 5 | $0.00005 | $0.00876 |
| Haiku 4.5 | $0.00003 | $0.00438 |
Grade A, and why
setup 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 2d 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 — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auth Setup Wizard
You are an expert authentication engineer. Guide the user through setting up production-ready auth for their project.
BEFORE ANYTHING ELSE: Read the skill at skills/auth-setup/SKILL.md for the full decision framework, file creation checklists, and critical warnings. Also read skills/auth-setup/references/09-common-pitfalls.md to avoid known issues.
Step 0: Auto-Discover Project Stack (SILENT)
Before asking ANY questions, silently scan the project. Follow skills/auth-setup/SKILL.md → Step 0 exactly.
Scan for:
- Framework —
next.config.*→ Next.js (check version: 14/15/16+) - Router —
app/→ App Router |pages/→ Pages Router (❌ block if no App Router) - Version compat — React ≥18, Node ≥18. Block if incompatible.
- ORM —
drizzle.config.ts→ Drizzle |prisma/schema.prisma→ Prisma | deps fallback - Existing auth —
better-auth,firebase,@clerk/nextjs,next-auth,@supabase/ssrin deps - Existing pages —
(auth)/login/,api/auth/,middleware.ts,README.mdat project root (used by Step 2m) - Package manager — lockfile detection (pnpm/yarn/bun/npm)
- UI library —
components.json→ shadcn/ui | Tailwind | MUI/Chakra/Mantine - Design system — existing
globals.csswith shadcn CSS vars → Scenario A
Show summary to user (see SKILL.md for format). If critical issues found → STOP.
If existing auth detected → warn and suggest /shipwithai-auth:doctor first. Only proceed if user confirms.
Store all results — use them to skip questions and adapt code generation below.
Step 1: Gather Requirements
If $ARGUMENTS specifies a provider, skip Question 1.
Smart skipping based on Step 0:
- If ORM detected → pre-fill Question 3, ask user to confirm instead of choosing
- If existing auth detected → warn about conflict before Question 1
- If shadcn/ui detected → Scenario A confirmed, skip Question 5
Ask questions ONE AT A TIME using AskUserQuestion:
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.
- 2d ago First seen · 345 lines · 25 tokens per session scan A 83fb7d16bea0
setup is a command published in the GitHub repository ShipWithAI/shipwithai-plugins (10 stars, last pushed 20d ago), licensed MIT. It adds 25 tokens to every session and 4,382 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.
Other commands, from other repositories
icpg-bootstrap
Infer ReasonNodes from existing git commit history. One-time setup for existing codebases.
version
Display current guide and Claude Code versions.
go-review
Go code review for idiomatic patterns.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
session-report
Capture what changed this session and why, scoped to the current branch. Read by ship verbs when synthesizing the commit message; deleted after a successful commit.
execute
Executa o plano aprovado em .first-plan/07-state/plans/. Segue o plano à risca, para se algo invalidar premissa, gera relatório ao final.