ship

ship is a command for Claude Code from isaacsight/kernel. It costs 0 tokens per session (768 once invoked), scanned A, original, MIT.

A release pipeline that runs security, quality, design, and other checks as a sequence of required gates.

In plain words
What is it for?
Use it to audit secrets and authentication, run TypeScript checks and builds, review design-system compliance, and record findings before deployment.
Why use it?
A failed check stops the release process, helping prevent known security problems, type errors, build failures, or serious design issues from being shipped.

Command for Claude Code

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.

agentmods
npx agentmods add commands/isaacsight/kernel/ship
Clone the repo
git clone --depth 1 https://github.com/isaacsight/kernel

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 ship

README.md
[![agentmods](https://agentmods.dev/badge/commands/isaacsight/kernel/ship.svg)](https://agentmods.dev/commands/isaacsight/kernel/ship)
Your own site
<a href="https://agentmods.dev/commands/isaacsight/kernel/ship"><img src="https://agentmods.dev/badge/commands/isaacsight/kernel/ship.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 768 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00000 $0.00768
Opus 5 $0.00000 $0.00384
Sonnet 5 $0.00000 $0.00154
Haiku 4.5 $0.00000 $0.00077

Measured yesterday against content hash 0f8b257d2ec6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ship scanned grade A 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 yesterday.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

4. Verify HTTP 200: `curl -s -o /dev/null -w "%{http_code}" https://kernel.chat`
.claude/commands/ship.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run the gated ship pipeline. Each gate must pass before proceeding to the next.

This is the flagship deployment command. It runs 6 agents in sequence, each as a gate. Any gate failure STOPS the pipeline.

Gate 1 — Security

Run the Security Agent protocol:

  1. Call agent_memory_read for security
  2. Run kernel_audit for vulnerability + secrets scan
  3. Grep src/ for hardcoded keys/tokens
  4. Verify edge function JWT configuration
  5. Call agent_memory_write for security with findings

STOP condition: Any P0 security finding (exposed secret, auth bypass)

Gate 2 — QA

Run the QA Agent protocol:

  1. Call agent_memory_read for qa
  2. Run npx tsc --noEmit — must pass with zero errors
  3. Run npm run build — must succeed
  4. Call agent_memory_write for qa with results

STOP condition: Type errors or build failure

Gate 3 — Design

Run the Designer Agent protocol:

  1. Call agent_memory_read for designer
  2. Run kernel_design_lint on recent changes
  3. Verify Rubin compliance (typography, palette, touch targets)
  4. Call agent_memory_write for designer with findings

STOP condition: Critical Rubin violation (wrong fonts, broken dark mode, inaccessible elements)

Gate 4 — Performance

Run the Performance Agent protocol:

  1. Call agent_memory_read for performance
  2. Check dist/assets/ bundle sizes after build (from Gate 2)
  3. Run kernel_deps for dependency check
  4. Call agent_memory_write for performance with metrics

STOP condition: JS bundle > 300KB gzip or CSS > 150KB gzip

Gate 5 — DevOps (Deploy)

Run the DevOps Agent protocol:

  1. Call agent_memory_read for devops
  2. Run npm run deploy
  3. Wait 30 seconds for propagation
  4. Verify HTTP 200: curl -s -o /dev/null -w "%{http_code}" https://kernel.chat
  5. Run kernel_uptime for full health check
  6. Call agent_memory_write for devops with deploy log

STOP condition: Deploy failure or health check failure. If failed, rollback with git revert HEAD --no-edit && npm run deploy

Read the full file on GitHub · 88 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. yesterday First seen · 88 lines · 0 tokens per session scan A 0f8b257d2ec6

Subscribe to this mod's changes

ship is a command published in the GitHub repository isaacsight/kernel (16 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 768 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.