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 hajekim/agentic-design-patterns-skills --skill prompt-chaininggit clone --depth 1 https://github.com/hajekim/agentic-design-patterns-skillsWrote 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/hajekim/agentic-design-patterns-skills/prompt-chaining)<a href="https://agentmods.dev/skills/hajekim/agentic-design-patterns-skills/prompt-chaining"><img src="https://agentmods.dev/badge/skills/hajekim/agentic-design-patterns-skills/prompt-chaining/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/hajekim/agentic-design-patterns-skills/prompt-chaining"><img src="https://agentmods.dev/badge/skills/hajekim/agentic-design-patterns-skills/prompt-chaining.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 | $0.00401 | $0.03301 |
| Opus 5 | $0.00200 | $0.01650 |
| Sonnet 5 | $0.00080 | $0.00660 |
| Haiku 4.5 | $0.00040 | $0.00330 |
Grade A, and why
prompt-chaining 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 10d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- prompt-chaining — 100% identical, 11 lines differ
How it starts
The opening of the file, as written. The whole thing — 311 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Chaining Pattern
Overview
Prompt Chaining (also known as the Pipeline Pattern) is a foundational agentic design pattern that breaks complex tasks into a sequence of smaller, focused sub-tasks. Rather than overwhelming a single LLM call with a multifaceted problem, each sub-task is addressed by a specifically crafted prompt, and the output of one step feeds as input to the next.
Core Principle: Divide-and-conquer — decompose the complex into a logical chain of manageable steps.
When This Skill Applies
Activate this pattern when:
- A task is too complex or multifaceted for a single prompt
- Multiple distinct processing stages are required
- Intermediate results need validation or transformation before the next step
- External tools or APIs must be called between reasoning steps
- You need to build agents capable of multi-step reasoning, planning, and decision-making
- The cognitive load on the model is causing instruction neglect, contextual drift, or hallucination
Rule of thumb: If a monolithic prompt struggles with multiple constraints and sequential reasoning steps, switch to prompt chaining.
Context Engineering
Context Engineering is the overarching discipline that governs how AI agents are designed — it is the practice of constructing and delivering the right informational environment to the model at every step of a pipeline. It is not just prompt writing; it is the systematic engineering of everything the model sees.
┌─────────────────────────────────────────────────────────────┐
│ CONTEXT WINDOW │
│ │
│ ┌──────────────┐ ┌───────────────┐ ┌────────────────┐ │
│ │ System Prompt│ │ RAG / Docs │ │ Tool Outputs │ │
│ │ (Role + │ │ (Retrieved │ │ (API results, │ │
│ │ Behavior) │ │ Knowledge) │ │ computations) │ │
│ └──────────────┘ └───────────────┘ └────────────────┘ │
│ │
│ ┌──────────────┐ ┌───────────────┐ │
│ │ State/History│ │ Structured │ │
│ │ (Prior chain │ │ Outputs │ │
│ │ outputs) │ │ (JSON/schema)│ │
│ └──────────────┘ └───────────────┘ │
└─────────────────────────────────────────────────────────────┘
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.
- 10d ago First seen · 311 lines · 401 tokens per session scan A 4784f93ab02e
prompt-chaining is a skill published in the GitHub repository hajekim/agentic-design-patterns-skills (4 stars, last pushed 5mo ago), licensed MIT. It adds 401 tokens to every session and 3,301 once invoked, about $0.0020 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 2026-08-31.
Other skills, from other repositories
prompt-optimizer
Analyze raw prompts, identify intent and gaps, match ECC components (skills/commands/agents/hooks), and output a ready-to-paste optimized prompt. Advisory role only — never executes the task itself. TRIGGER when: user says "optimize prompt", "improve my prompt", "how to write a prompt for", "help me prompt", "rewrite…
gemini-api
Google Gemini API patterns for Python and TypeScript. Covers content generation, streaming, tool use (function calling), vision, system instructions, context caching, batch requests, and agent workflows. Use when building applications with the Gemini API or Google Generative AI SDKs.
image-prompt
A Korean-language skill that turns a rough image idea into a detailed prompt for gpt-image-2, OpenAI’s image-generation model.
regex-vs-llm-structured-text
Decision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases.
foundation-models-on-device
Apple FoundationModels framework for on-device LLM — text generation, guided generation with @Generable, tool calling, and snapshot streaming in iOS 26+.
seedance-antislop
Detect and remove hollow AI filler language, empty superlatives, and vague boosters that degrade Seedance 2.0 prompt quality. Use when a prompt feels generic, over-written, or 'AI-sounding', or when generation output looks bland and needs a quality pass.