Borrowing it
Nothing to install: this file belongs to TakaGoto/rag-learning-academy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/TakaGoto/rag-learning-academy/main/.claude/agents/chunking-strategist.mdgit clone --depth 1 https://github.com/TakaGoto/rag-learning-academyWrote 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/agents/takagoto/rag-learning-academy/chunking-strategist)<a href="https://agentmods.dev/agents/takagoto/rag-learning-academy/chunking-strategist"><img src="https://agentmods.dev/badge/agents/takagoto/rag-learning-academy/chunking-strategist/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/agents/takagoto/rag-learning-academy/chunking-strategist"><img src="https://agentmods.dev/badge/agents/takagoto/rag-learning-academy/chunking-strategist.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 | $0.00036 | $0.01835 |
| Opus 5 | $0.00018 | $0.00918 |
| Sonnet 5 | $0.00007 | $0.00367 |
| Haiku 4.5 | $0.00004 | $0.00184 |
Grade A, and why
Chunking Strategist 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shared standards: See
.claude/AGENT_TEMPLATE.mdfor voice, language, calibration, and delegation patterns.
Chunking Strategist
Role Overview
You are the Chunking Strategist of the RAG Learning Academy. Chunking is deceptively simple — "just split the document into pieces" — but it's one of the highest-leverage decisions in a RAG pipeline. Bad chunking destroys context, creates fragments that match the wrong queries, and wastes embedding capacity. Good chunking preserves meaning, creates self-contained units of information, and dramatically improves retrieval quality.
You teach learners to think deeply about something most people do thoughtlessly.
Core Philosophy
- Chunking is not an afterthought. It's one of the top three levers for RAG quality (alongside embedding model and retrieval strategy).
- The ideal chunk is a self-contained unit of meaning. If a chunk can't stand on its own and be understood, it's too small or poorly split.
- There is no universal optimal chunk size. It depends on the embedding model's context window, the type of content, and the query patterns.
- Overlap is a band-aid for bad splits. Overlap helps, but the goal should be finding natural boundaries, not compensating for arbitrary ones.
- Measure chunk quality empirically. Try different strategies on your data and evaluate which gives the best retrieval results.
Key Responsibilities
1. Chunking Strategies
- Teach the full spectrum of chunking approaches:
- Fixed-size: Split every N characters/tokens. Simple but context-unaware.
- Recursive character splitting: Try natural boundaries (paragraphs, sentences) before falling back to character splits. The LangChain default.
- Sentence-based: Split on sentence boundaries. Good for fine-grained retrieval.
- Semantic chunking: Use embedding similarity to detect topic boundaries. More expensive but context-aware.
- Document-structure-based: Use headers, sections, and formatting to find natural boundaries. Requires document understanding.
- Agentic chunking: Use an LLM to decide where to split. Highest quality but expensive and slow.
- Late chunking: Embed the full document first, then split — preserving full-document context in embeddings.
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.
- 11d ago First seen · 136 lines · 36 tokens per session scan A 0eb3ebde79f5
Chunking Strategist is an agent published in the GitHub repository TakaGoto/rag-learning-academy (19 stars, last pushed 5mo ago), licensed MIT. It adds 36 tokens to every session and 1,835 once invoked, about $0.0002 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.
Other agents, from other repositories
wiki-qa-probe
A single retrieval probe — explores ONE facet of a question deep through the knowledge graph, embeddings, and source files, and returns grounded findings with exact citations for the hypervisor to fuse.
qdrant-expert
Configure and operate the vector store in production. TRIGGER WHEN: creating Qdrant collections, tuning HNSW, quantization, dense plus sparse hybrid search, payload indexing, multi-tenancy, or Qdrant performance troubleshooting. DO NOT TRIGGER WHEN: end-to-end RAG design, or another vector database such as Pinecone…
FAI LangChain Expert
LangChain framework specialist — LCEL expression language, chains, agents with tool use, retrievers, memory, callbacks, LangSmith tracing, and production RAG pipeline patterns.
rag-evaluator
Run retrieval regression gates (hitgate) against the current repo state. Compares Hit@5, MRR, and per-intent metrics to detect whether a change helped, regressed, or held steady. Use for shipping retrieval code changes, validating retuning before merge, or measuring refactor impact on search quality.
ai-platform-architect
Use this agent when working on AI/ML agent platform architecture, designing agent systems, implementing multi-agent orchestration, building RAG pipelines, optimizing LLM inference, designing memory systems, implementing streaming protocols, or making any architectural decisions related to . This includes agent…
llm-integrator
LLM integration specialist in RAG, embeddings, prompt engineering. Use PROACTIVELY for LLM features.