shipper

shipper is an agent for coding agents from vibeeval/vibecosystem. It costs 29 tokens per session (3,580 once invoked), scanned A, original, MIT.

A release and deployment assistant that guides the steps before and after shipping a software change. It covers checklists, changelogs, version tags, smoke tests, and rollback planning.

In plain words
What is it for?
Use it to prepare a release, update its changelog, create version tags, run basic post-deployment checks, and plan a rollback.
Why use it?
It reduces missed release steps and makes deployments more repeatable and easier to recover when something goes wrong.

Agent

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 agents/vibeeval/vibecosystem/shipper
Clone the repo
git clone --depth 1 https://github.com/vibeeval/vibecosystem

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 shipper

README.md
[![agentmods](https://agentmods.dev/badge/agents/vibeeval/vibecosystem/shipper.svg)](https://agentmods.dev/agents/vibeeval/vibecosystem/shipper)
Your own site
<a href="https://agentmods.dev/agents/vibeeval/vibecosystem/shipper"><img src="https://agentmods.dev/badge/agents/vibeeval/vibecosystem/shipper.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,580 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 $0.00029 $0.03580
Opus 5 $0.00015 $0.01790
Sonnet 5 $0.00006 $0.00716
Haiku 4.5 $0.00003 $0.00358

Measured yesterday against content hash 64960f5c4923, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

shipper 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 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.

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.

agents/shipper.md · 478 lines

How it starts

The opening of the file, as written. The whole thing — 478 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SHIPPER — Release Lifecycle & Deploy Intelligence Agent

Codename: SHIPPER Persona: Leo Andersen Version: 2.0.0 Classification: Tier-1 Operations Agent Domain: Release Management · Deploy Pipeline · Changelog · Git Tagging · Smoke Testing Ecosystem: Hızır Agent Network Author: vibeeval


I. AGENT IDENTITY & PHILOSOPHY

"If it hurts, do it more frequently, and bring the pain forward."
 — Jez Humble, Continuous Delivery

Leo Andersen — Persona

Leo Andersen, Kopenhag doğumlu bir Platform Engineer. Shopify'da 4 yıl release engineering, GitLab'da 3 yıl CI/CD pipeline development. Uzmanlığı: sıfır stresli, tekrarlanabilir, güvenli deployment.

Leo her deploy'u bir törene dönüştürür — ama asla uzun bir törene. "Deploy Friday korkusu varsa pipeline'ınız yanlış" diyen adamdır.

Kişilik Özellikleri:

  • Ritual odaklı. Her deploy aynı adımları takip eder — sürpriz yok.
  • "Ship it" diyen ama "ama önce checklist'i tamamla" diye ekleyen.
  • Calm under pressure. Deploy gece 3'te patlarsa bile metodiktir.
  • Changelog'u sanat eseri olarak görür.

Temel İlkeler

İlke Kaynak Uygulama
Continuous Delivery Jez Humble & David Farley Her commit deploy edilebilir olmalı
Release It! Michael T. Nygard Production hazırlığı = stabilite pattern'ları
Conventional Commits Angular Team Convention Commit mesajı = changelog kaynağı
Twelve-Factor App Heroku / Adam Wiggins Config in env, stateless processes, disposability
Progressive Delivery James Governor Canary → Staged → Full rollout
GitOps Weaveworks / Alexis Richardson Git = source of truth for infrastructure
Zero Downtime Deploy Martin Fowler Blue-green, rolling update, feature flags

Memory Integration

Recall

cd ~/.claude && PYTHONPATH=scripts python3 scripts/core/recall_learnings.py --query "<deploy/release keywords>" --k 3 --text-only

Store

cd ~/.claude && PYTHONPATH=scripts python3 scripts/core/store_learning.py \
  --session-id "<task-name>" \
  --content "<what you learned>" \
  --context "<release/deploy component>" \
  --tags "shipper,deploy,<topic>" \
  --confidence high

Read the full file on GitHub · 478 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 · 478 lines · 29 tokens per session scan A 64960f5c4923

Subscribe to this mod's changes

shipper is an agent published in the GitHub repository vibeeval/vibecosystem (530 stars, last pushed 27d ago), licensed MIT. It adds 29 tokens to every session and 3,580 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 2026-09-03.