ship-gate

ship-gate is a skill for Claude Code, Codex from chadcorp/warden. It costs 0 tokens per session (534 once invoked), scanned A, original, Apache-2.0.

A final release-check procedure that independently decides whether a finished deliverable is ready to publish. It verifies calculations, sources, files, and empty or extreme cases.

In plain words
What is it for?
Use it before shipping software, publishing research or content, or handing over a completed deliverable.
Why use it?
It catches missing files, unsupported claims, incorrect numbers, and edge-case failures that can be overlooked during building.

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/chadcorp/warden/ship-gate
Any agent
npx skills add chadcorp/warden --skill ship-gate
Clone the repo
git clone --depth 1 https://github.com/chadcorp/warden

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-gate

README.md
[![agentmods](https://agentmods.dev/badge/skills/chadcorp/warden/ship-gate.svg)](https://agentmods.dev/skills/chadcorp/warden/ship-gate)
Your own site
<a href="https://agentmods.dev/skills/chadcorp/warden/ship-gate"><img src="https://agentmods.dev/badge/skills/chadcorp/warden/ship-gate.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 534 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 $0.00000 $0.00534
Opus 5 $0.00000 $0.00267
Sonnet 5 $0.00000 $0.00107
Haiku 4.5 $0.00000 $0.00053

Measured 4d ago against content hash 151c3ac7c601, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ship-gate 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/build-brain/ship-gate/SKILL.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ship Gate

An independent GO/NO-GO release gate. It runs cold on a finished deliverable, trusts no claim from the build log, and blocks on a small set of unwaivable conditions. Its job is to catch the thing the builder, tired and close to the work, can no longer see.

When to use

"Is it ready to ship?", "Gate this", "Final check before publishing", or before anything goes out the door.

The protocol

  1. Forget the build story. Read only the artifacts. The build log's "it works" is hearsay; the gate re-derives the truth from the deliverable itself.

  2. Re-derive the numbers. Take the headline figures and recompute them a second, independent way from the raw inputs. If a total does not reconcile, that is a blocking NO-GO.

  3. Re-check the facts. Every cited figure, date, rate, or rule must trace to a dated primary source (delegate to research-brain/fact-gate). An unsourced factual claim is a NO-GO.

  4. Confirm the files. The artifacts named in the deliverable must exist, open, and contain what the listing says. A promised file that is missing or empty is a NO-GO.

  5. Check the empty and edge states. Open the product with no data and with extreme data. A view that breaks or shows a wrong value is a NO-GO.

  6. Screen for policy and honesty. No claim you cannot stand behind, no "100% guaranteed," no figure you could not reproduce. Honesty is a gate condition, not a nicety.

The unwaivable conditions (any one ⇒ NO-GO)

  • A headline number that does not reconcile a second way.
  • A factual claim with no dated primary source.
  • A named artifact that is missing, empty, or unopenable.
  • A broken empty/edge state.
  • A claim that overstates what the product does.
  • A policy violation in the user-facing surface.

Output

A one-line GO or NO-GO, then the evidence: what was re-derived, what was re-checked, and — on NO-GO — the exact blocking condition and how to clear it.

Honesty rule

A gate that always says GO is decoration. The respectful act is to block a real problem before a buyer finds it.

Read the full file on GitHub · 51 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 51 lines · 0 tokens per session scan A 151c3ac7c601

Subscribe to this mod's changes

ship-gate is a skill published in the GitHub repository chadcorp/warden (0 stars, last pushed 2mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 534 tokens. 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.

Related

Other skills, from other repositories

publish

Publish the Octop Python package: cut a release branch from develop, bump version, update CHANGELOG, open a PR to main; after merge, Actions tag on main (PyPI / Docker Hub + GHCR) and sync main into develop. Use when the user asks to publish, release, bump version, cut a release, or run /publish.

TencentCloud/Octop · 74 tokens

updater_guide

Guidance for checking for and installing Row-Bot updates.

siddsachar/row-bot · 17 tokens

code-review

Performs structured code review on a file or directory.

Alex8791-cyber/cognithor · 13 tokens

backup

Automated hourly backup skill that creates timestamped archives of Cognithor config files, skill definitions, and data directories on a cron schedule. Use when setting up automated backups, restoring from snapshots, scheduling data protection, or configuring backup retention policies.

Alex8791-cyber/cognithor · 51 tokens

gmail-sync

API integration skill that fetches Gmail messages, syncs inbox labels, and processes attachments via the Gmail REST API. Use when fetching new emails, syncing inbox state, triaging unread messages, exporting mail data, or integrating Gmail into automated workflows.

Alex8791-cyber/cognithor · 52 tokens

test

Diagnostic smoke-test skill that validates Cognithor's skill loading, SkillRegistry registration, and Planner-Gatekeeper-Executor pipeline. Use when running a framework health check, verifying skill setup works end-to-end, debugging skill registration, or smoke-testing after configuration changes.

Alex8791-cyber/cognithor · 55 tokens