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 agentmods add skills/deploygate/deploygate-agent-plugin/setupnpx skills add DeployGate/deploygate-agent-plugin --skill setupgit clone --depth 1 https://github.com/DeployGate/deploygate-agent-pluginWhat 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 | $0.00018 | $0.04597 |
| Opus 5 | $0.00009 | $0.02299 |
| Sonnet 5 | $0.00004 | $0.00919 |
| Haiku 4.5 | $0.00002 | $0.00460 |
Grade A, and why
setup 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.
How it starts
The opening of the file, as written. The whole thing — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Response Language
Detect the user's language from their first message in the conversation.
If they wrote in Japanese, use the (ja) block at every user-facing
location below. Otherwise (English or any other language), use the
(en) block. If unsure, default to (en).
User-facing locations are written as paired blocks marked (en) and
(ja). Use only one — never both. This applies to: AskUserQuestion
text, progress-display labels, and any prose you quote to the user.
Internal instructions, code blocks, file paths, tool names, and JSON
examples stay English regardless of language.
DeployGate Onboarding
Guide users through setting up DeployGate for app distribution — from first upload to team-wide deployment.
When to use
When the user wants to:
- Set up DeployGate for the first time
- Upload and distribute an app
- Get started with DeployGate
Reference files
Load these on demand when the flow reaches the matching step. Do NOT preload them — each file is substantial and wastes context if unused.
references/terminology.md— Read this first, before writing any user-facing response. Defines the user-facing terms (Workspace / Project / Team / Shared Team) and their Japanese equivalents.references/ios-build.md— iOS build detail: fastlane vs xcodebuild, code signing pre-flight, Personal Team pitfall. Read when handling iOS in Step 2.references/ios-udid.md— Step 5b UDID registration flow (fastlane register_devices / sigh). Read when a tester cannot install an Ad Hoc build.references/next-steps.md— Phase 2+ guidance (CI/CD, SDK, team expansion). Read after Phase 1 completes.references/troubleshooting.md— troubleshooting table. Read on error.
Progress Display
At the beginning of each step, display a progress indicator. Use ✅ for completed, ▶ for current, and ○ for upcoming. Android skips Step 5.
Android example (at Step 3) — (en):
📋 Phase 1: DeployGate Setup [3/4]
Step 1 ✅ Account creation
Step 2 ✅ App upload
Step 3 ▶ Distribution page ← now
Step 4 ○ Notification setup
What ships with it
5 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.
- yesterday First seen · 326 lines · 18 tokens per session scan A a2700183f183
setup is a skill published in the GitHub repository DeployGate/deploygate-agent-plugin (3 stars, last pushed 6d ago), licensed MIT. It adds 18 tokens to every session and 4,597 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 2026-08-31.
Other skills, from other repositories
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
wiki
Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.
marketplace-publish-validation
Corezoid marketplace pre-publication validator. Standalone skill — no external skill dependencies required. Use this skill whenever the user wants to publish, release, or submit a project or folder to the Corezoid marketplace, or asks to check if a project is ready to publish. Activate on phrases: "publish to…