prompt-chaining

prompt-chaining is a skill for Claude Code, Codex from hajekim/agentic-design-patterns-skills. It costs 401 tokens per session (3,301 once invoked), scanned A, original, MIT.

A workflow pattern that splits a complex request into smaller prompts, passing each result to the next step.

In plain words
What is it for?
Use it to build sequential agent workflows where steps transform, validate, or extend earlier results.
Why use it?
It makes multi-stage tasks easier to manage and check than one large request.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Gemini CLI.

Good fit Use it to build sequential agent workflows where steps transform, validate, or extend earlier results.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hajekim/agentic-design-patterns-skills/prompt-chaining
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.

Any agent
npx skills add hajekim/agentic-design-patterns-skills --skill prompt-chaining
Clone the repo
git clone --depth 1 https://github.com/hajekim/agentic-design-patterns-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for prompt-chaining

README.md
[![agentmods](https://agentmods.dev/badge/skills/hajekim/agentic-design-patterns-skills/prompt-chaining/github.svg)](https://agentmods.dev/skills/hajekim/agentic-design-patterns-skills/prompt-chaining)
Your own site
<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.

agentmods 80×15 button for prompt-chaining

Your own site · 80×15
<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>
Per session 401 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,301 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00401 $0.03301
Opus 5 $0.00200 $0.01650
Sonnet 5 $0.00080 $0.00660
Haiku 4.5 $0.00040 $0.00330

Measured 10d ago against content hash 4784f93ab02e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/prompt-chaining/SKILL.md · 311 lines

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)│                       │
│  └──────────────┘  └───────────────┘                       │
└─────────────────────────────────────────────────────────────┘

Read the full file on GitHub · 311 lines

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. 10d ago First seen · 311 lines · 401 tokens per session scan A 4784f93ab02e

Subscribe to this mod's changes

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.

Related

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…

Jamkris/everything-gemini-code · 179 tokens

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.

Jamkris/everything-gemini-code · 57 tokens

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.

daeryundf2-prog/LAZYANTIGRAVITY · 651 tokens

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.

Jamkris/everything-gemini-code · 38 tokens

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+.

Jamkris/everything-gemini-code · 38 tokens

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.

Kingdaddy007/my-os · 61 tokens