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 joao-aires/agent-skills-public --skill ai-developmentgit clone --depth 1 https://github.com/joao-aires/agent-skills-publicWrote 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/joao-aires/agent-skills-public/ai-development)<a href="https://agentmods.dev/skills/joao-aires/agent-skills-public/ai-development"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/ai-development/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/joao-aires/agent-skills-public/ai-development"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/ai-development.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00057 | $0.01639 |
| Opus 5.5 | $0.00023 | $0.00656 |
| Sonnet 5.5 | $0.00011 | $0.00328 |
| Haiku 4.5 | $0.00006 | $0.00164 |
Grade A, and why
ai-development 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.
How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Develop AI applications and integrations
Start from the user outcome, operating constraints and existing system. Choose the smallest combination of models, deterministic services, agent capabilities and interfaces that can meet it. This method supports focused design, implementation, review and operating work; it does not start a full application lifecycle or authorize live actions on its own. MCP-only and skill-authoring work need no model or agent framework merely to use this guidance.
Define the task and system boundary
Establish actors, inputs, outputs, consequential errors and observable acceptance.
- Identify what requires inference or generation and what ordinary application code can decide more reliably.
- Reuse accepted product, architecture and interface decisions.
- Resolve material data-use, licensing, security, reliability and cost constraints before dependent commitments; seek the relevant available expertise without assuming another plugin exists.
Choose how much of the task the model needs to control. If the rules are known and inputs can be validated, ordinary application code may be sufficient. A bounded model call fits a task that needs inference but has a defined input and output. An application-owned workflow keeps sequencing and recovery in code while allowing model judgments at selected points. An agent runtime is useful when the next action genuinely depends on what the model discovers, but it also needs limits, supervision and a way to account for partial work.
Compare these approaches against the actual uncertainty and action needs. Keep the parts with hard correctness requirements under deterministic control, even when an agent chooses the next step. For application-type choices and architecture tradeoffs, read application patterns. Use a framework for a justified orchestration capability, durable execution for work that must survive interruption, and multiple agents when distinct responsibilities improve the task enough to justify coordination. Do not introduce these layers to complete a technology checklist.
What ships with it
3 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 Changed · +33 lines 4a89e2c9359f
- 2d ago First seen · 65 lines · 57 tokens per session scan A 17506e62194c
ai-development is a skill published in the GitHub repository joao-aires/agent-skills-public (2 stars, last pushed yesterday), licensed MIT. It adds 57 tokens to every session and 1,639 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-20.
Other skills, from other repositories
embeddings
Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching, simple lookups, no semantic understanding needed.
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
9router-embeddings
Generate vector embeddings via 9Router /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.
similarity-search-patterns
Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.
embedding-strategies
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.