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 ai-agent-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/ai-agent-builder)<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/ai-agent-builder"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/ai-agent-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/ai-agent-builder"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/ai-agent-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00090 | $0.02435 |
| Opus 5 | $0.00045 | $0.01218 |
| Sonnet 5 | $0.00018 | $0.00487 |
| Haiku 4.5 | $0.00009 | $0.00244 |
Grade A, and why
ai-agent-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 8d 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 — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Agent Builder
Critères de choix du pattern
| Complexité | Pattern recommandé | Framework |
|---|---|---|
| Tâche unique, 1-5 outils | ReAct (Reasoning + Acting) | LangChain, SDK natif |
| Tâche longue multi-étapes | Plan-and-Execute | LangGraph |
| Exploration de solutions alternatives | Tree of Thoughts | LangGraph + custom |
| Équipe de spécialistes | Multi-agent orchestré | CrewAI, AutoGen, LangGraph |
| Workflow avec état persistant et branchements | Stateful graph | LangGraph |
Règle de base : commencer par ReAct. Passer à Plan-and-Execute si l'agent doit coordonner plus de 5 étapes séquentielles. Passer au multi-agent si les domaines de compétence sont orthogonaux (ex : code + recherche + rédaction).
Workflow en étapes
1. Rédiger le system prompt de l'agent
Structure minimale :
Tu es [RÔLE]. Tu [OBJECTIF PRINCIPAL].
Règles :
- Tu réponds uniquement sur [DOMAINE].
- Tu n'inventes pas de données.
- Si tu manques d'information, utilise l'outil [NOM_OUTIL] avant de répondre.
Finalisation : quand tu as la réponse, utilise l'outil `final_answer`.
Inclure : rôle, périmètre, règles de refus, format de sortie attendu, condition d'arrêt explicite.
2. Définir les outils (tool schemas)
Format Anthropic (compatible aussi OpenAI avec adaptation mineure) :
tools = [
{
"name": "search_web",
"description": "Recherche des informations récentes sur le web. Utiliser si la question porte sur des faits susceptibles d'avoir changé récemment.",
"input_schema": {
"type": "object",
"properties": {
"query": {"type": "string", "description": "Requête de recherche optimisée"}
},
"required": ["query"]
}
},
{
"name": "run_python",
"description": "Exécute du code Python et retourne stdout + stderr. Utiliser pour calculs, transformations de données.",
"input_schema": {
"type": "object",
"properties": {
"code": {"type": "string", "description": "Code Python à exécuter"}
},
"required": ["code"]
}
}
]
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.
- 8d ago First seen · 248 lines · 90 tokens per session scan A bf328ad1c5b5
ai-agent-builder is a skill published in the GitHub repository khalilbenaz/claude-skills-collection (22 stars, last pushed 18d ago), licensed MIT. It adds 90 tokens to every session and 2,435 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
json-mode-patterns
Structured JSON output from Claude: tool-use-as-JSON, schema, parsing, partial recovery. Triggers: JSON mode, structured output, schema validation, JSON parsing.
model-strategy
Multi-model orchestration and model-switching strategy. Score-based model selection, reasoning-effort routing, cross-agent delegation (Gemini, Codex, Ollama), advisor pairing, escalation triggers, permission matrix, and cost-efficiency optimization.
creator-prompt-engineer
Convert creative-department outputs (script, vision, cinematography, characters, sets, storyboards, shots) into producible, consistent AI image/video prompts — with tool-specific optimization, locked anchors, negative prompts, and safe alternatives. Default image tool priority for storyboard/character sheets is GPT…
roo-fix-volatile-msg
Ladder-aware Roo Code Anthropic caching — verify the rolling read/write ladder on the wire, then close the real gaps (Vertex 4-block budget, MiniMax path).
prompt-engineer
Use this skill when the user explicitly asks to create, write, improve, or optimize a prompt for use with an AI. Trigger on phrases like "write me a prompt", "improve this prompt", "create a system prompt", "how do I ask ChatGPT/Claude to...", or "quero um prompt para...". Do NOT trigger for direct task requests where…
midjourney-prompter
Engineer Midjourney prompts — style references, aspect ratios, negative prompts, and v6 parameter tuning.