giselle: Skill for Claude Code

.claude/skills/add-model/SKILL.md

add-model is a skill for Claude Code from giselles-ai/giselle. It costs 45 tokens per session (750 once invoked), scanned A, original, Apache-2.0.

A code guide for adding a language model, an AI model that generates or understands text, to the Giselle codebase.

In plain words
What is it for?
Use it to register OpenAI, Anthropic, or Google models, define their limits and capabilities, update configuration, and run project checks.
Why use it?
It gives developers the required model details and the files that must stay consistent when a provider adds a model.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is giselles-ai/giselle's own configuration. It tells Claude Code how to work on giselle itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything giselle configures →

Reuse

Borrowing it

Nothing to install: this file belongs to giselles-ai/giselle. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/giselles-ai/giselle/main/.claude/skills/add-model/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/giselles-ai/giselle

Made for: Claude Code.

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 add-model

README.md
[![agentmods](https://agentmods.dev/badge/skills/giselles-ai/giselle/add-model/github.svg)](https://agentmods.dev/skills/giselles-ai/giselle/add-model)
Your own site
<a href="https://agentmods.dev/skills/giselles-ai/giselle/add-model"><img src="https://agentmods.dev/badge/skills/giselles-ai/giselle/add-model/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.

agentmods 80×15 button for add-model

Your own site · 80×15
<a href="https://agentmods.dev/skills/giselles-ai/giselle/add-model"><img src="https://agentmods.dev/badge/skills/giselles-ai/giselle/add-model.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 750 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00045 $0.00750
Opus 5 $0.00023 $0.00375
Sonnet 5 $0.00009 $0.00150
Haiku 4.5 $0.00005 $0.00075

Measured 12d ago against content hash 56f637faca93, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

add-model 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 12d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • add-model — 100% identical, 0 lines differ
.claude/skills/add-model/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Add Language Model

Add a new language model to the Giselle codebase with full system consistency.

Quick Start

  1. Gather model specifications (or search web for official docs)
  2. Update files in order listed below
  3. Run validation: pnpm format && pnpm build-sdk && pnpm check-types && pnpm tidy && pnpm test

Required Information

Before starting, collect:

  • Provider: openai, anthropic, or google
  • Model ID: e.g., "gpt-5.3", "claude-opus-5"
  • Context window: Maximum input tokens
  • Max output tokens: Maximum output tokens
  • Knowledge cutoff: Date of training data cutoff
  • Pricing: Input/output cost per million tokens
  • Capabilities: Reasoning, image input, web search, etc.
  • Configuration options: Reasoning effort levels, verbosity, temperature, etc.

Files to Update (In Order)

1. Language Model Registry (Primary Definition)

File: packages/language-model-registry/src/{provider}.ts

Add the model definition. See REGISTRY.md for detailed examples.

2. Language Model Package

File: packages/language-model/src/{provider}.ts

Update three locations:

  1. Add to the enum (e.g., OpenAILanguageModelId)
  2. Add regex catch for dated versions in .catch() block
  3. Create model instance and add to models array

See LANGUAGE-MODEL.md for detailed examples.

3. Model Pricing

File: packages/language-model/src/costs/model-prices.ts

Add pricing entry to the appropriate table. See PRICING.md.

4. AI SDK Transformation

File: packages/giselle/src/generations/v2/language-model/transform-giselle-to-ai-sdk.ts

Add model ID to the switch case for the provider.

5. Node Conversion

File: packages/node-registry/src/node-conversion.ts

Add bidirectional conversion:

  • Short to full: case "model-id": return "provider/model-id";
  • Full to short: case "provider/model-id": return "model-id";

6. UI Configuration (If Needed)

File: internal-packages/workflow-designer-ui/src/editor/properties-panel/text-generation-node-properties-panel/model/{provider}.tsx

Read the full file on GitHub · 91 lines

Files

What ships with it

7 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. 12d ago First seen · 91 lines · 45 tokens per session scan A 56f637faca93

Subscribe to this mod's changes

add-model is a skill published in the GitHub repository giselles-ai/giselle (555 stars, last pushed 11d ago), licensed Apache-2.0. It adds 45 tokens to every session and 750 once invoked, about $0.0002 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

adversarial-ml-evasion

Craft adversarial examples that cause trained ML classifiers to misclassify at inference time — image recognition, malware detectors, IDS, spam filters.

PurpleAILAB/Decepticon · 36 tokens

llm-redteam-overview

LLM red team category — full AATMF v3 tactic coverage (T01–T15). Routing skill: read this first to identify which tactic applies, then load the matching sub-skill. Maps to MITRE ATLAS where overlap exists.

PurpleAILAB/Decepticon · 58 tokens

misinformation

Hunt LLM misinformation / overreliance (OWASP LLM09:2025) — confident-but-wrong outputs that flow into downstream automated decisions, compliance reports, customer communications, or autonomous code commits without verification.

PurpleAILAB/Decepticon · 49 tokens

sensitive-information-disclosure

Hunt LLM sensitive-information disclosure (OWASP LLM02:2025) — leakage of PII, secrets, internal source, model details, and other-tenant data through model outputs, training-data extraction, or retrieval-side joins.

PurpleAILAB/Decepticon · 55 tokens

vector-and-embedding-weaknesses

Hunt vector / embedding weaknesses (OWASP LLM08:2025) — adversarial inputs against the RAG / similarity layer that cause cross-tenant leak, embedding-inversion privacy loss, semantic confusion, and retriever-driven prompt injection.

PurpleAILAB/Decepticon · 59 tokens

aatmf-t12-rag-poisoning

AATMF T12 — RAG & Knowledge Base Manipulation. PoisonedRAG, vector store flood, embedding collision, retrieval-bias attacks.

PurpleAILAB/Decepticon · 41 tokens