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.
npx skills add takaoumehara/superforge-skill --skill superforge-shipgit clone --depth 1 https://github.com/takaoumehara/superforge-skillWrote 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.
[](https://agentmods.dev/skills/takaoumehara/superforge-skill/superforge-ship)<a href="https://agentmods.dev/skills/takaoumehara/superforge-skill/superforge-ship"><img src="https://agentmods.dev/badge/skills/takaoumehara/superforge-skill/superforge-ship/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/takaoumehara/superforge-skill/superforge-ship"><img src="https://agentmods.dev/badge/skills/takaoumehara/superforge-skill/superforge-ship.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00267 | $0.03720 |
| Opus 5 | $0.00133 | $0.01860 |
| Sonnet 5 | $0.00053 | $0.00744 |
| Haiku 4.5 | $0.00027 | $0.00372 |
Grade A, and why
superforge-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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Superforge Ship — the release gate
superforge-verify answers "does it work?" with runtime evidence. This
skill answers a different question that has stopped more launches:
"Are we allowed to release this, and will we be able to tell what happened after we do?"
A product can pass every test and still be unshippable — because it collects data it never disclosed, because the store will reject it for a reason nobody checked, because there is no way to turn it off if it goes wrong, or because it ships with no instrumentation and the first month produces feelings instead of facts.
0. The gate rule
Never report "ready to ship" as prose. End every run with one code:
| Verdict | Meaning |
|---|---|
SHIP |
Every blocker below is cleared, or explicitly does not apply, with the reason recorded |
BLOCK |
At least one blocker is unresolved. Name it, name what clears it, stop |
RISK-ACCEPTED |
A known gap is being shipped deliberately. Requires: what the gap is, what it could cost, who decided, and when it gets fixed. Undated risk acceptance is just BLOCK with better manners |
A gate that always returns SHIP is decoration. If nothing has ever come back
BLOCK, the checks are not being run.
1. Legal — what the product's own behaviour has triggered
The single fact that makes this checkable rather than infinite:
Jurisdiction follows your users, not your address. A developer in New York, in Tokyo, or anywhere else faces the same obligations, determined by where the people using the product are and what data is touched.
That is why this gate is universal, and why "I'm not in Europe" is never the answer to a GDPR question — one EU user is enough.
Work in this order, always: what data does it touch → who does that reach → what does that oblige → what must be visible before launch.
The trigger tables — data categories, regional triggers, sensitive-category
escalation, children, subscription disclosure, and the explicit list of
situations where a lawyer stops being optional — are in
references/legal-triggers.md.
What ships with it
11 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.
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.
- 9d ago First seen · 306 lines · 267 tokens per session scan A 514e92b78456
superforge-ship is a skill published in the GitHub repository takaoumehara/superforge-skill (1 stars, last pushed 24d ago), licensed MIT. It adds 267 tokens to every session and 3,720 once invoked, about $0.0013 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.
Other skills, from other repositories
lov-china-website-filing
A workflow for preparing and launching websites in mainland China, including ICP filing and public-security filing. ICP filing is the registration required for many mainland websites, while public-security filing is a separate police registration.
lov-review-doc
A contract review assistant for agreements such as NDAs, service contracts, data agreements, employment contracts, licences, and investment documents. It can analyse risks, add comments, and suggest revised wording.
contract-review-pro
Professional-grade contract review skill that adds comment-based issue annotations without changing original text. Enforces a four-layer review (entity verification, basic, business, legal), writes structured comments (issue type, risk reason, revision suggestion) with risk level encoded via reviewer name, and…
lov-legal-pages
A website content tool that drafts privacy policy and terms-of-service pages from the project’s real business and data-handling facts. These pages explain how a service uses information and what rules apply to its users.
lov-domain-cutover
A workflow for putting a mainland-China website online after its ICP filing is approved. It verifies the deployment, DNS, HTTPS certificate, domain response, ICP footer, and handling of the old domain.
lov-filing-monitor
A recurring checker for website filing status on official Chinese government or service-provider pages. It compares the latest status with the previous check and keeps a record.