forge-ship

forge-ship is a skill for Claude Code, Codex from SidCorp-co/forge. It costs 55 tokens per session (768 once invoked), scanned A, original, Apache-2.0.

A workflow skill for the final stages of software work: merging approved changes, checking deployment requirements, writing a changelog entry, and closing the issue.

In plain words
What is it for?
Use it after review approval to merge into the configured base branch, run the required deployment gate, record the change, and close the issue.
Why use it?
It helps ensure that approved code is actually landed and accounted for, and prevents closing work when a deployment is broken or blocked.

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/sidcorp-co/forge/forge-ship
Any agent
npx skills add SidCorp-co/forge --skill forge-ship
Clone the repo
git clone --depth 1 https://github.com/SidCorp-co/forge

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 forge-ship

README.md
[![agentmods](https://agentmods.dev/badge/skills/sidcorp-co/forge/forge-ship.svg)](https://agentmods.dev/skills/sidcorp-co/forge/forge-ship)
Your own site
<a href="https://agentmods.dev/skills/sidcorp-co/forge/forge-ship"><img src="https://agentmods.dev/badge/skills/sidcorp-co/forge/forge-ship.svg" alt="Measured on agentmods" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 768 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 $0.00055 $0.00768
Opus 5 $0.00028 $0.00384
Sonnet 5 $0.00011 $0.00154
Haiku 4.5 $0.00006 $0.00077

Measured 3d ago against content hash f4aaff881131, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

forge-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 3d 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.

packages/runner/skills/forge-ship/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

forge-ship

The review approved. Two things left: land it, and account for it.

Merge

Into the base branch you checked out from. That is yours and needs no permission.

Resolve the target from the project's own configuration, not from the plan text and not from habit — a project whose base branch changed will have stale branch names written into older issue descriptions, and following them merges into the wrong place silently.

Merging anywhere else needs a human. Ask, do not assume.

If the merge conflicts, that is phase 3 again, not a failure: re-declare code, resolve, and come back through review if the resolution changed behaviour.

Deploy gate

projectFacts.deploy-policy says whether a deploy happens on this project and what gates it. You request it; the cloud allows it or does not. A refusal is not an error to work around — if deploy is gated, the gate is the answer.

If a deploy runs and does not come up, do not close the issue. Comment with what you saw and set needs_info. A green merge with a dead deploy is the exact state that looks finished and is not.

Account for it

One comment. It is the only record a human will read, so it carries everything that is not in the diff:

Section Content
What changed one paragraph, in terms of the reported problem, not the files
Extra fixes defects you fixed that were not in the acceptance criteria
Left unresolved anything you found and did not fix, and why
Verification what you ran, and what it said

Left unresolved is not optional and it is not a confession. Something out of reach leaves as one of: a blocks edge onto the issue that would ship without it, a line in docs/proposals/, or this comment saying plainly that a human must decide. It does not leave as a new issue.

Changelog

One line under ## [Unreleased], written for someone who does not know this issue exists. If the change is invisible to users, say so and write nothing — an entry that says "refactored internals" is noise in a file people read to find out what changed for them.

Read the full file on GitHub · 72 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. 3d ago First seen · 72 lines · 55 tokens per session scan A f4aaff881131

Subscribe to this mod's changes

forge-ship is a skill published in the GitHub repository SidCorp-co/forge (5 stars, last pushed 3d ago), licensed Apache-2.0. It adds 55 tokens to every session and 768 once invoked, about $0.0003 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.