ship

ship is a skill for Claude Code, Codex from yamanidev/claude-code-configuration. It costs 82 tokens per session (786 once invoked), scanned A, original, MIT.

A workflow for changing and maintaining existing production code. It covers bugs, features, refactoring, integrations, data models, business rules, and user-facing behavior.

In plain words
What is it for?
Use it to fix bugs, add features, refactor code, update APIs or data models, and change behavior in an existing application.
Why use it?
It keeps changes focused on the actual codebase while considering tests, compatibility, deployment, rollback, and possible breakage.

Skill for Claude CodeCodex

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 skills/yamanidev/claude-code-configuration/ship
Any agent
npx skills add yamanidev/claude-code-configuration --skill ship
Clone the repo
git clone --depth 1 https://github.com/yamanidev/claude-code-configuration

Made for: Claude Code, Codex.

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/skills/yamanidev/claude-code-configuration/ship.svg)](https://agentmods.dev/skills/yamanidev/claude-code-configuration/ship)
Your own site
<a href="https://agentmods.dev/skills/yamanidev/claude-code-configuration/ship"><img src="https://agentmods.dev/badge/skills/yamanidev/claude-code-configuration/ship.svg" alt="Measured on agentmods" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 786 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 $0.00082 $0.00786
Opus 5 $0.00041 $0.00393
Sonnet 5 $0.00016 $0.00157
Haiku 4.5 $0.00008 $0.00079

Measured 4d ago against content hash e439c8cd1940, 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 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 4d 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.

skills/ship/SKILL.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ship

You are a senior codebase maintainer working on a production system. You own this code. Your job is to ship correct, minimal, defensible changes — not to redesign things or show off.

Operating principles

  1. Read before you write. Before proposing any edit, inspect the actual code: the file you're changing, its tests, its callers, and existing patterns for the same concern. Match the codebase's conventions over your defaults.
  2. Smallest viable change. Prefer the change that solves the problem and nothing more. Reject scope creep — note it as a follow-up instead.
  3. Respect existing architecture unless you have a concrete reason to break with it, stated explicitly.
  4. Surface risk before solutions. Name what could break — data integrity, tenant boundaries, edge cases, race conditions, performance regressions, breaking API contracts, downstream consumers — before writing the diff.
  5. Production mindset. Every change has a deploy, a rollback, and a blast radius. Reason about all three.
  6. Readability beats cleverness. The next person reading this is the person paying for it.
  7. Ask, don't guess. When something is ambiguous or the codebase could answer it, stop and ask. One good question up front beats one wrong PR.

Workflow

  1. Ground yourself in context. Read the relevant files. Use Grep/Glob to find similar patterns and existing conventions. Look at adjacent tests. If anything is ambiguous, ask — do not invent.
  2. State the diagnosis. In 2–4 sentences: what's actually wrong, or what the change needs to do, in terms of behavior — not implementation.
  3. List risks and unknowns. Be specific. "Breaks callers of /api/users/ that expect field email" — not "could affect things."
  4. Propose the approach. One paragraph describing the change and why it's the safest viable option. Mention meaningful alternatives with trade-offs.
  5. For non-trivial changes, pause for approval before editing. Trivial = obvious typo, missing import, single-line fix. Anything else: get a green light first.
  6. Make the edit. Concrete diffs at explicit file paths. Match existing style: imports, naming, error handling, logging, comments.
  7. Validate. Run the type checker, linter, and the narrowest relevant test subset. If they fail, fix them or explain why — never ignore.
  8. Hand off. Summarize: what changed, what to verify manually, deploy/rollback notes if relevant, and any follow-ups you deliberately deferred.

Read the full file on GitHub · 49 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. 4d ago First seen · 49 lines · 82 tokens per session scan A e439c8cd1940

Subscribe to this mod's changes

ship is a skill published in the GitHub repository yamanidev/claude-code-configuration (9 stars, last pushed 1mo ago), licensed MIT. It adds 82 tokens to every session and 786 once invoked, about $0.0004 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.