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 khalilbenaz/claude-skills-collection --skill openai-assistants-buildergit clone --depth 1 https://github.com/khalilbenaz/claude-skills-collectionWrote 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/khalilbenaz/claude-skills-collection/openai-assistants-builder)<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/openai-assistants-builder"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/openai-assistants-builder/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/khalilbenaz/claude-skills-collection/openai-assistants-builder"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/openai-assistants-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 79 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00116 | $0.02625 |
| Opus 5 | $0.00058 | $0.01313 |
| Sonnet 5 | $0.00023 | $0.00525 |
| Haiku 4.5 | $0.00012 | $0.00263 |
Grade A, and why
openai-assistants-builder 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 13d 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 — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenAI Assistants Builder — API Assistants v2
Critères de décision : Assistants API vs Chat Completions
| Besoin | Assistants API | Chat Completions |
|---|---|---|
| Mémoire de conversation persistante | ✅ Threads gérés par OpenAI | ❌ À gérer soi-même |
| Recherche sémantique dans des fichiers | ✅ file_search natif | ❌ RAG custom requis |
| Exécution de code Python | ✅ code_interpreter sandbox | ❌ Sandbox custom requis |
| Latence minimale (< 500ms) | ❌ Overhead run lifecycle | ✅ Réponse directe |
| Contrôle total du contexte | ❌ Géré par OpenAI | ✅ Contrôle complet |
| Coût optimisé (volume élevé) | ❌ + coût tools/storage | ✅ Tokens seuls |
Choisir Assistants API pour les MVP avec RAG ou analyse de données sans backend complexe. Choisir Chat Completions quand la latence, le coût, ou le contrôle du contexte sont prioritaires.
Workflow en 10 étapes
1. Installation et initialisation
pip install openai>=1.57.0 tenacity
from openai import OpenAI
import os
client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])
# Azure OpenAI (optionnel) :
# from openai import AzureOpenAI
# client = AzureOpenAI(
# azure_endpoint=os.environ["AZURE_OPENAI_ENDPOINT"],
# api_key=os.environ["AZURE_OPENAI_KEY"],
# api_version="2024-05-01-preview",
# )
2. Création de l'assistant (une seule fois)
assistant = client.beta.assistants.create(
name="Assistant Commercial",
model="gpt-4o", # ou gpt-4o-mini pour réduire les coûts
instructions=(
"Vous êtes un assistant commercial expert. "
"Répondez en français, citez vos sources documentaires. "
"Soyez concis et professionnel."
),
tools=[
{"type": "file_search"},
{"type": "code_interpreter"},
{
"type": "function",
"function": {
"name": "get_product_price",
"description": "Consulte le prix d'un produit dans le catalogue",
"parameters": {
"type": "object",
"properties": {
"product_id": {"type": "string", "description": "ID produit (ex: PROD001)"}
},
"required": ["product_id"],
},
},
},
],
temperature=0.2, # Réduire pour des réponses plus déterministes
response_format="auto", # ou {"type":"json_object"} pour JSON structuré
)
# IMPORTANT : stocker cet ID — ne jamais recréer l'assistant à chaque appel
print(f"ASSISTANT_ID={assistant.id}") # Persister dans .env ou config
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.
- 13d ago First seen · 279 lines · 116 tokens per session scan A a1c5ca3085b3
openai-assistants-builder is a skill published in the GitHub repository khalilbenaz/claude-skills-collection (22 stars, last pushed 19d ago), licensed MIT. It adds 116 tokens to every session and 2,625 once invoked, about $0.0006 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.
Other skills, from other repositories
llm-integration
Integrate OpenAI and Anthropic APIs with streaming, structured output, tool calling, token management, and cost optimization.
sglang
Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.
llm-provider
Adds a new LLM provider implementing LLMProvider interface with call() and stream() methods. Integrates with provider factory in src/llm/index.ts, config detection in src/llm/config.ts, and error handling via tracking and recovery. Use when adding a new model backend, integrating a third-party LLM API, or extending…
calling-llms
Use when sending chat completions through liter-llm and routing to a specific provider via the provider/model prefix. Covers the chat call shape, provider routing, modelhint, message roles, and error categories.
streaming-responses
Use when streaming tokens incrementally from an LLM via liter-llm over SSE or async iterators. Covers chatstream, delta handling, and null-content chunks.
api-patterns
API design: naming, versioning, pagination, idempotency, OpenAPI, error contracts and safe retries. Triggers: API design, REST, GraphQL, OpenAPI, Swagger, error response, HTTP status, rate limit.