add-generation-support

A workflow for connecting an already defined machine-learning ecosystem to a system that generates models or related outputs. It adds the graph, handler, configuration, discriminator, and router wiring needed by the generation form.

In plain words
What is it for?
Use it after add-ecosystem when an existing provider needs generation support, or when generation must be re-enabled or given a new graph and handler pair.
Why use it?
It prevents an ecosystem from being listed in project data but missing from the interface and workflow that actually generate results.

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/civitai/civitai/add-generation-support
Any agent
npx skills add civitai/civitai --skill add-generation-support
Clone the repo
git clone --depth 1 https://github.com/civitai/civitai

Made for: Claude Code, Codex.

Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,549 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 $0.00078 $0.06549
Opus 5 $0.00039 $0.03275
Sonnet 5 $0.00016 $0.01310
Haiku 4.5 $0.00008 $0.00655

Measured yesterday against content hash d05bc4aea9f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

add-generation-support 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.

.claude/skills/add-generation-support/SKILL.md · 463 lines

How it starts

The opening of the file, as written. The whole thing — 463 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Add Generation Support

Wires an existing ecosystem (already defined in basemodel.constants.ts) into the generation form. Requires the ecosystem, base model, license, and family to already exist — use the add-ecosystem skill first if any of those are missing.

When to use

  • After add-ecosystem for a new provider
  • To re-enable generation for an ecosystem that was previously commented out
  • When adding a new graph/handler pair for an existing ecosystem that didn't have one

Prerequisites check

Before starting, confirm the ecosystem exists in basemodel.constants.ts:

  • ECO.<Name> is defined
  • An EcosystemRecord exists in ecosystems
  • A BaseModelRecord exists in baseModelRecords

If any are missing, stop and direct the user to run add-ecosystem first.

Workflow (interactive after research)

1. Check @civitai/client for ecosystem-specific types

Always check the latest published client version, even if types aren't in the currently installed version.

# Check installed version
grep "@civitai/client" c:/Work/model-share/package.json

# Check latest available
npm view @civitai/client versions --json | tail -20

Search the latest version's types for the ecosystem:

cd /tmp && npm pack @civitai/client@<latest-version> 2>/dev/null
tar -xzf civitai-client-<latest-version>.tgz
grep -n "<EcosystemName>\|<ecosystem-name>" /tmp/package/dist/generated/types.gen.d.ts

Note what you find (or don't find):

  • Ecosystem-specific types (e.g., SeedanceVideoGenInput, ComfyErnieStandardCreateImageGenInput): use them — they give you the exact field shape and strict enum literals
  • Multiple variant types (e.g., standard vs turbo): the handler will branch on model version and return the appropriate typed input
  • No types at all: fall back to the generic ImageGenStepTemplate / VideoGenStepTemplate with a string engine field

Read the full file on GitHub · 463 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. yesterday First seen · 463 lines · 78 tokens per session scan A d05bc4aea9f0

Subscribe to this mod's changes

add-generation-support is a skill published in the GitHub repository civitai/civitai (7,241 stars, last pushed today), licensed Apache-2.0. It adds 78 tokens to every session and 6,549 once invoked, about $0.0004 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 2026-08-30.

Related

Other skills, from other repositories

find-missing-translations

Use when comparing Android strings.xml locale files to find untranslated string resources, missing translation keys, or preparing translation work for a specific language.

vitorpamplona/amethyst · 32 tokens

quartz-integration

Integration guide for using the Quartz Nostr KMP library in external projects. Use when: (1) adding Quartz as a Gradle dependency, (2) setting up NostrClient with WebSocket, (3) creating/signing/sending events, (4) building relay subscriptions with Filter, (5) handling keys with KeyPair/NostrSignerInternal, (6) using…

vitorpamplona/amethyst · 161 tokens

android-expert

Android platform patterns for the amethyst/ module. Use when working with (1) Android navigation (Navigation Compose, type-safe routes, bottom nav), (2) runtime permissions (camera, notifications, biometrics), (3) platform APIs (Intent, Context, Activity, ContentResolver), (4) Material3 theming and edge-to-edge UI…

vitorpamplona/amethyst · 149 tokens

kotlin-coroutines-structured-concurrency

Use when writing or reviewing Kotlin code that stores CoroutineScope, launches from init/non-suspending APIs, calls runBlocking, or catches broad exceptions around suspend calls. Technique-layer skill — complements the codebase-specific kotlin-coroutines.

vitorpamplona/amethyst · 55 tokens

kotlin-expert

Advanced Kotlin patterns for AmethystMultiplatform. Flow state management (StateFlow/SharedFlow), sealed hierarchies (classes vs interfaces), immutability (@Immutable, data classes), DSL builders (type-safe fluent APIs), inline functions (reified generics, performance). Use when working with: (1) State management…

vitorpamplona/amethyst · 148 tokens

compose-expert

Advanced Compose Multiplatform UI patterns for shared composables. Use when working with visual UI components, state management patterns (remember, derivedStateOf, produceState), recomposition optimization (@Stable/@Immutable visual usage), Material3 theming, custom ImageVector icons, or determining whether to share…

vitorpamplona/amethyst · 98 tokens