chunking-strategy

chunking-strategy is a skill for Claude Code from giuseppe-trisciuoglio/developer-kit. It costs 69 tokens per session (1,469 once invoked), scanned A, original, MIT.

Guidance for splitting documents into smaller sections for retrieval-augmented generation, a method where an AI searches stored documents before answering. It covers section size, overlap, document structure, and retrieval quality.

In plain words
What is it for?
For designing or tuning document-processing and vector-search systems, including workflows for Markdown, code, tables, PDFs, HTML, JSON, and other structured content.
Why use it?
It helps avoid sections that are too large to search accurately or so small that their meaning is lost.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the developer-kit-ai plugin — 3 skills, 1 command, 1 agent shipped together

not rated 343repo +5 21d ago A scan Socket: passSnyk: passSkillSpector: pass 69 tokens original MIT

Good fit For designing or tuning document-processing and vector-search systems, including workflows for Markdown, code, tables, PDFs, HTML, JSON, and other structured content.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/giuseppe-trisciuoglio/developer-kit/chunking-strategy
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 giuseppe-trisciuoglio/developer-kit --skill chunking-strategy
Clone the repo
git clone --depth 1 https://github.com/giuseppe-trisciuoglio/developer-kit

Made for: Claude Code.

Or install developer-kit-ai, the plugin that ships this one along with the rest of its 3 skills, 1 command, 1 agent.

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 chunking-strategy

README.md
[![agentmods](https://agentmods.dev/badge/skills/giuseppe-trisciuoglio/developer-kit/chunking-strategy/github.svg)](https://agentmods.dev/skills/giuseppe-trisciuoglio/developer-kit/chunking-strategy)
Your own site
<a href="https://agentmods.dev/skills/giuseppe-trisciuoglio/developer-kit/chunking-strategy"><img src="https://agentmods.dev/badge/skills/giuseppe-trisciuoglio/developer-kit/chunking-strategy/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 chunking-strategy

Your own site · 80×15
<a href="https://agentmods.dev/skills/giuseppe-trisciuoglio/developer-kit/chunking-strategy"><img src="https://agentmods.dev/badge/skills/giuseppe-trisciuoglio/developer-kit/chunking-strategy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,469 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. Third-party audits
  • Socket pass 1 Apr 2026
  • Snyk pass 1 Apr 2026
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00069 $0.01469
Opus 5 $0.00034 $0.00734
Sonnet 5 $0.00014 $0.00294
Haiku 4.5 $0.00007 $0.00147

Measured 9d ago against content hash 50e95b88a2e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

chunking-strategy 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 9d 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/developer-kit-ai/skills/chunking-strategy/SKILL.md · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Chunking Strategy for RAG Systems

Overview

Provides chunking strategies for RAG systems, vector databases, and document processing. Recommends chunk sizes, overlap percentages, and boundary detection methods; validates semantic coherence; evaluates retrieval metrics.

When to Use

Use when building or optimizing RAG systems, vector search pipelines, document chunking workflows, or performance-tuning existing systems with poor retrieval quality.

Instructions

Choose Chunking Strategy

Select based on document type and use case:

  1. Fixed-Size Chunking (Level 1)

    • Use for simple documents without clear structure
    • Start with 512 tokens and 10-20% overlap
    • Adjust: 256 for factoid queries, 1024 for analytical
  2. Recursive Character Chunking (Level 2)

    • Use for documents with structural boundaries
    • Hierarchical separators: paragraphs → sentences → words
    • Customize for document types (HTML, Markdown, JSON)
  3. Structure-Aware Chunking (Level 3)

    • Use for structured content (Markdown, code, tables, PDFs)
    • Preserve semantic units: functions, sections, table blocks
    • Validate structure preservation post-split
  4. Semantic Chunking (Level 4)

    • Use for complex documents with thematic shifts
    • Embedding-based boundary detection with 0.8 similarity threshold
    • Buffer size: 3-5 sentences
  5. Advanced Methods (Level 5)

    • Late Chunking for long-context models
    • Contextual Retrieval for high-precision requirements
    • Monitor computational cost vs. retrieval gain

Reference: references/strategies.md.

Implement Chunking Pipeline

  1. Pre-process documents

    • Analyze structure, content types, information density
    • Identify multi-modal content (tables, images, code)
  2. Select parameters

    • Chunk size: embedding model context window / 4
    • Overlap: 10-20% for most cases
    • Strategy-specific settings
  3. Process and validate

    • Apply chunking strategy
    • Validate coherence: run evaluate_chunks.py --coherence (see below)
    • Test with representative documents

Read the full file on GitHub · 196 lines

Files

What ships with it

8 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.

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. 9d ago First seen · 196 lines · 69 tokens per session scan A 50e95b88a2e0

Subscribe to this mod's changes

chunking-strategy is a skill published in the GitHub repository giuseppe-trisciuoglio/developer-kit (343 stars, last pushed 21d ago), licensed MIT. It adds 69 tokens to every session and 1,469 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

unity-llm-integration

Use when adding LLM/chat/RAG features to a Unity game or tool: API keys, prompt assets, safety, latency, and server-side vs client-side calls.

rachitkumarrastogi/unity-mcp-server · 41 tokens

java-spring-ai

Use when the user asks to add AI features, integrate Spring AI or LangChain4J, build a chatbot, implement RAG (retrieval-augmented generation), use vector stores, stream LLM responses, or call AI tools/functions in a Spring Boot project.

ducpm2303/claude-java-plugins · 59 tokens

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…

google/skills · 85 tokens

langchain

Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG…

davila7/claude-code-templates · 79 tokens

llamaindex

Data framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features vector indices, query engines, agents, and multi-modal support. Use for document Q&A, chatbots, knowledge retrieval, or building RAG pipelines. Best for data-centric LLM…

davila7/claude-code-templates · 70 tokens

graphify

Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community…

Graphify-Labs/graphify · 76 tokens