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/ci-setupnpx skills add DeployGate/deploygate-agent-plugin --skill ci-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 | $0.01085 |
| Opus 5 | $0.00009 | $0.00543 |
| Sonnet 5 | $0.00004 | $0.00217 |
| Haiku 4.5 | $0.00002 | $0.00109 |
Grade A, and why
ci-setup scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `references/external-ci.md` — CircleCI / Codemagic / curl-based integration. Read for anything other than GitHub Actions or Bitrise How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DeployGate CI/CD Setup
Guide users through setting up CI/CD integration for automated app uploads and PR-based distribution.
When to use
When the user wants to:
- Automate DeployGate uploads from CI
- Set up PR-based distribution pages
- Integrate DeployGate with GitHub Actions, Bitrise, CircleCI, or other CI
Reference files
Load only what matches the detected CI provider and project type. Each file is substantial (full YAML templates) — do NOT preload.
references/github-actions-upload.md— GitHub Actions main-branch upload workflow template (full YAML with Android + iOS examples). Read when generating the main-branch workflowreferences/github-actions-pr.md— GitHub Actions PR distribution workflow template (full YAML with comment / deployment / cleanup logic). Read when generating the PR workflowreferences/ios-code-signing.md— iOS code signing setup for CI (fastlane match vs manual .p12 + ASC API key). Read when the project is iOSreferences/bitrise.md— Bitrise DeployGate upload step. Read for Bitrisereferences/external-ci.md— CircleCI / Codemagic / curl-based integration. Read for anything other than GitHub Actions or Bitrisereferences/troubleshooting.md— troubleshooting table. Read on error
Step 1: Detect CI Environment
Check the project for existing CI configuration:
.github/workflows/→ GitHub Actions (native integration available)bitrise.yml→ Bitrise (official DeployGate step available).circleci/config.yml→ CircleCI (curl-based upload)codemagic.yaml→ Codemagic (curl-based upload)- None found → Recommend GitHub Actions for new setup
Also detect the project type:
build.gradle/build.gradle.kts→ Android (runs on ubuntu-latest)*.xcodeproj/*.xcworkspace→ iOS (requires macos-latest runner)
Step 2: Configure Secrets
For CI, recommend using the project API key instead of a personal API key. Project API keys are not tied to a specific user, so CI won't break when team members leave or change roles.
What ships with it
6 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 · 113 lines · 18 tokens per session scan A 29f40c48a857
ci-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 1,085 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
superloopy-clone
Use when the user asks for Superloopy clone or asks to clone, rebuild, reverse-engineer, replicate, or copy a website or page into a Superloopy-governed implementation. Triggers on "loopy clone", target URLs plus requests such as "clone this site", "rebuild this page", "make a copy of this website", "pixel-perfect…
flutter-ui
Build Flutter UI from Figma MCP or image input. Scans src for design tokens (colors, sizes, text styles), existing components, and naming conventions before writing a single line of code. Never hard-codes values.
audit-frontend-design
Use when reviewing or changing a React, Next.js, Tailwind, or shadcn interface and you need evidence-backed findings for accessibility, hierarchy, tokens, states, and responsive design before editing code.
bootstrap-xcode-workspace
Create, adopt, extend, and align one Swift product workspace with app, extension, package, and service components under one permanent Xcode entrypoint.
hermes-agent-compatibility
Audit Socket-to-Hermes compatibility across Agent Skills, Codex plugins, MCP, hooks, apps, agents, and Hermes extension systems. Use for skill exports, config translations, and Hermes adapter decisions.
gradle-agp-workflow
Inspect and maintain Android Gradle and Android Gradle Plugin workflows, including Gradle wrapper policy, AGP and Kotlin plugin versions, Java toolchains, Android SDK settings, namespaces, variants, flavors, signing config, version catalogs, dependencies, generated sources, build cache boundaries, and targeted…