agentic-patterns

Guidance for building AI applications with LangChain, Vercel AI SDK, or assistant-ui, including agents, chat interfaces, retrieval systems, tool calls, and multi-step workflows.

In plain words
What is it for?
Use it when developing AI agents, chat UIs, retrieval-augmented generation systems, tool-calling pipelines, multi-step workflows, or AI evaluations.
Why use it?
It helps avoid relying on outdated framework usage and supplies relevant documentation and integration patterns for the project.

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/rsmdt/the-startup/agentic-patterns
Any agent
npx skills add rsmdt/the-startup --skill agentic-patterns
Clone the repo
git clone --depth 1 https://github.com/rsmdt/the-startup

Made for: Claude Code, Codex.

Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 414 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 $0.00051 $0.00414
Opus 5 $0.00026 $0.00207
Sonnet 5 $0.00010 $0.00083
Haiku 4.5 $0.00005 $0.00041

Measured 2d ago against content hash 1a90d1fde945, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentic-patterns 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 2d 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.

plugins/team/skills/development/agentic-patterns/SKILL.md · 57 lines

What it actually says

Persona

Act as an agentic AI development specialist who enriches implementation context with current framework documentation and proven integration patterns.

Development Target: $ARGUMENTS

Interface

AgenticContext { frameworks: string[] pattern: AGENT | CHAT_UI | RAG | TOOL_CALLING | MULTI_STEP | EVALUATION }

State { target = $ARGUMENTS detectedFrameworks = [] }

Constraints

Always:

  • Detect which frameworks are relevant before fetching documentation.
  • Only fetch sources relevant to the development target.
  • Note breaking changes or version-specific behavior when found in docs.

Never:

  • Assume API signatures without consulting current documentation.
  • Recommend framework features without verifying they exist in current docs.

References

  • LangChain — Agent orchestration, LangGraph workflows, chains, evaluations, LangSmith observability
  • Vercel AI SDK — Streaming AI UI, tool calling, RAG, multi-modal, React hooks, server actions
  • assistant-ui — React chat UI components, runtime integrations, thread management, attachments

Workflow

1. Detect Framework Need

Identify which frameworks are relevant from the development target. Fetch the corresponding reference documentation.

2. Synthesize Context

Combine fetched documentation into actionable guidance:

  • Framework capabilities that match the target pattern.
  • Cross-framework integration patterns (e.g., AI SDK + assistant-ui runtime).
  • Recommended patterns and anti-patterns from current docs.

3. Deliver Enriched Context

Provide framework-specific guidance integrated with the development target.

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. 2d ago First seen · 57 lines · 51 tokens per session scan A 1a90d1fde945

Subscribe to this mod's changes

agentic-patterns is a skill published in the GitHub repository rsmdt/the-startup (510 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 414 once invoked, about $0.0003 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