doc/semantic-chunking

doc/semantic-chunking is a skill for Claude Code, Codex from denn-gubsky/loomcycle. It costs 27 tokens per session (359 once invoked), scanned A, original, Apache-2.0.

A text-organization tool that turns prose or Markdown into a hierarchy of smaller, titled sections in a document.

In plain words
What is it for?
Use it to import specifications, notes, or other prose as meaningful parent and child sections, with optional section types and workflow statuses.
Why use it?
It prevents long text from becoming one difficult-to-edit block and preserves the document’s existing structure and topic changes.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to import specifications, notes, or other prose as meaningful parent and child sections, with optional section types and workflow statuses.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/denn-gubsky/loomcycle/semantic-chunking
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 denn-gubsky/loomcycle --skill semantic-chunking
Clone the repo
git clone --depth 1 https://github.com/denn-gubsky/loomcycle

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 doc/semantic-chunking

README.md
[![agentmods](https://agentmods.dev/badge/skills/denn-gubsky/loomcycle/semantic-chunking/github.svg)](https://agentmods.dev/skills/denn-gubsky/loomcycle/semantic-chunking)
Your own site
<a href="https://agentmods.dev/skills/denn-gubsky/loomcycle/semantic-chunking"><img src="https://agentmods.dev/badge/skills/denn-gubsky/loomcycle/semantic-chunking/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 doc/semantic-chunking

Your own site · 80×15
<a href="https://agentmods.dev/skills/denn-gubsky/loomcycle/semantic-chunking"><img src="https://agentmods.dev/badge/skills/denn-gubsky/loomcycle/semantic-chunking.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 359 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 $0.00027 $0.00359
Opus 5 $0.00014 $0.00179
Sonnet 5 $0.00005 $0.00072
Haiku 4.5 $0.00003 $0.00036

Measured 9d ago against content hash dc7b06e8b914, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

doc/semantic-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 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.

bundles/document-agent/skills/doc/semantic-chunking/SKILL.md · 31 lines

What it actually says

Semantic chunking

When the operator hands you a body of text (pasted prose, a spec, a Markdown file) and asks to "import it" or "chunk it", turn it into a hierarchy of chunks — do NOT dump it into one giant chunk.

Method

  1. Read the text's own structure first: existing headings, numbered sections, topic shifts, and natural paragraphs are your chunk boundaries.
  2. Choose a hierarchy: a top-level chunk per major section, child chunks per sub-section. Aim for chunks that are individually meaningful and editable — a few sentences to a few paragraphs each, not one-liners and not whole pages.
  3. Give every chunk a short, descriptive title (it becomes the heading).
  4. Create them top-down so parents exist before children: Document op=create_chunk document_id=<id> parent_id=<parent> title="…" body="…" (omit parent_id for a child of the root, or pass the document's root chunk).
  5. Carry a type when the operator's domain implies one (e.g. section, requirement, task) and a status if they use a workflow.

Notes

  • If the text is a loomcycle export (it has <!-- loom: … --> comments), prefer the deterministic import_md op instead (see the doc/md-import skill).
  • Keep the operator's wording in the body; don't paraphrase unless asked.
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 · 31 lines · 27 tokens per session scan A dc7b06e8b914

Subscribe to this mod's changes

doc/semantic-chunking is a skill published in the GitHub repository denn-gubsky/loomcycle (13 stars, last pushed today), licensed Apache-2.0. It adds 27 tokens to every session and 359 once invoked, about $0.0001 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

pdf-processing

Extract text and tables from PDF files, fill forms, merge documents. Use when working with PDF files or when the user mentions PDFs, forms, or document extraction.

Tencent/WeKnora · 36 tokens

co-mail-and-drive

Read and send mail from the user's own Gmail or Outlook account, safely stage Gmail draft attachments, send from the agent's own address, manage Outlook contacts, and work with Google Drive files — with co gmail, co outlook, co email, and co gdrive. Use when the user asks about their inbox, an email or draft they want…

openonion/connectonion · 92 tokens

weknora-shared

Use when driving a WeKnora RAG server through the weknora CLI as an agent — authenticating, managing knowledge bases / documents / sessions / agents, running search or chat, or interpreting the CLI's JSON envelopes and exit codes. Read this before any other weknora- skill.

Tencent/WeKnora · 68 tokens

weknora-rag-search

Use when retrieving from or asking questions against a WeKnora knowledge base via the weknora CLI — and especially when unsure whether to use chat, session ask, or search chunks for a given goal.

Tencent/WeKnora · 54 tokens

upload-artifact

Upload a file as a ClosedLoop document (PRD, implementation plan, feature, or template). Reads file content and uploads via MCP without consuming conversation context. Also supports creating new versions of existing documents. Triggers on: "upload artifact", "upload PRD", "upload implementation plan", "upload…

closedloop-ai/claude-plugins · 103 tokens

extract-plan-md

Sync plan.md with plan.json content. MUST be used after ANY edit to plan.json to keep plan.md in sync. Triggers: After editing plan.json with Edit tool (REQUIRED - always sync after edits) User asks to "sync plan.md", "update plan.md", "extract the md from a plan" Converting plan.json to markdown or viewing plan as…

closedloop-ai/claude-plugins · 99 tokens