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 agentmods add skills/agentsope/skillalchemy/agentsop-multiscale-chunkingnpx skills add agentsope/SkillAlchemy --skill agentsop-multiscale-chunkinggit clone --depth 1 https://github.com/agentsope/SkillAlchemyWrote 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/agentsope/skillalchemy/agentsop-multiscale-chunking)<a href="https://agentmods.dev/skills/agentsope/skillalchemy/agentsop-multiscale-chunking"><img src="https://agentmods.dev/badge/skills/agentsope/skillalchemy/agentsop-multiscale-chunking.svg" alt="Measured on agentmods" 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 | $0.00092 | $0.04962 |
| Opus 5 | $0.00046 | $0.02481 |
| Sonnet 5 | $0.00018 | $0.00992 |
| Haiku 4.5 | $0.00009 | $0.00496 |
Grade A, and why
agentsop-multiscale-chunking 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.
How it starts
The opening of the file, as written. The whole thing — 359 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-scale Chunking · C5 Enhancement Overlay
Overlay on top of [[llamaindex]]. The base skill teaches the 5-layer RAG pipeline and lists
DecoupleChunkScopeas one optimization knob among many. This overlay zooms in on that single knob and turns it into a standalone recipe: how to resolve the chunk paradox when one chunk size is provably not enough. Third-person analytical view for an agent writing / reviewing RAG ingestion code — not an end-user tutorial.
1. 何时激活 (Activation Rules)
Activate this overlay when all three RAG preconditions hold and the chunk paradox has actually surfaced:
- The corpus is long documents — prose manuals, financial filings, legal contracts, research papers, codebases — where a single answer-bearing fact sits inside a larger context that the LLM needs to interpret it.
- A chunk-size sweep has stalled: small chunks (128–256) win retrieval precision but the LLM answers from fragments; large chunks (1024–2048) give rich context but recall on specific queries drops because the embedding becomes a "topic average". The official failure-mode checklist documents both poles as separate failures — #2 (wrong chunk from too-small) and #6 (context overflow / dilution from too-large) (cited in [[llamaindex]] R3).
- Faithfulness or relevancy is plateauing below target and bumping
chunk_sizeonly moves the failure from one pole to the other.
Concrete triggers:
- "Answers are technically retrieved but the model lacks context to explain them."
- "I keep retuning chunk_size and it never wins on both faithfulness and recall."
- A reviewer sees
SentenceSplitter(chunk_size=4096)shipped as the fix for "incomplete answers" (this is anti-pattern A1 in [[llamaindex]]).
Do not activate when:
- The corpus is short/static (<100k tokens) — prompt-stuff with caching; multi-scale chunking is over-engineering (§6).
- The chunk-size sweep did converge on a single winner (e.g. 1024 for prose) — pin it and stop.
- Retrieval quality is fine and the bottleneck is orchestration or synthesis.
What ships with it
3 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.
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.
- 2d ago Changed · -7 lines · -133 tokens per session 12a2e1027361
- 6d ago First seen · 366 lines · 225 tokens per session scan A 7e5045b32dcf
agentsop-multiscale-chunking is a skill published in the GitHub repository agentsope/SkillAlchemy (361 stars, last pushed 3d ago), licensed MIT. It adds 92 tokens to every session and 4,962 once invoked, about $0.0005 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 skills, from other repositories
karpathy-llm-wiki
Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.
mixedbread-search
Build and query managed search indexes (Stores) using the Mixedbread Python and TypeScript SDKs. Use when creating knowledge bases, uploading documents, performing semantic or vector search, asking questions over documents, using agentic multi-step retrieval, combining store search with web results, filtering by…
mxbai-cli
Use the mxbai CLI to manage stores, upload files, search documents, ask questions, and sync directories from the terminal. Use when performing Mixedbread operations via command line, setting up CI/CD pipelines with store sync, or managing API keys.
ccg-docs
Generate Markdown documentation from code graphs, build RAG indexes for AI consumption, and lint documentation quality.
rag-evaluator
Generates tailored giskard.checks evaluation suites for RAG (Retrieval-Augmented Generation) systems. Use whenever a user describes a Q&A bot grounded in documents, a knowledge-base chatbot, a retrieval system, or wants to evaluate answer groundedness, faithfulness, hallucination, retrieval quality, citation accuracy…
local-rag-mcp
Use when querying, ingesting, or maintaining a local RAG MCP corpus for semantic document retrieval with privacy controls.