llm-wiki-kit: Instructions file for Claude Code

CLAUDE.md

llm-wiki-kit CLAUDE.md is an instructions file for Claude Code from SantiagoBobrik/llm-wiki-kit. It costs 762 tokens per session, scanned A, original, MIT.

Repository instructions for maintaining a personal wiki built on an Obsidian vault, a note-taking system. The repository contains Claude Code skills and the writing rules they apply to notes.

In plain words
What is it for?
Use them when editing the wiki skills, updating the contract template, or working with raw clippings, generated articles, indexes, and compile logs.
Why use it?
They give the coding agent the project structure and editing contract, reducing mistakes when changing the skills or wiki files.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is SantiagoBobrik/llm-wiki-kit's own configuration. It tells Claude Code how to work on llm-wiki-kit itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything llm-wiki-kit configures →

Reuse

Borrowing it

Nothing to install: this file belongs to SantiagoBobrik/llm-wiki-kit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/SantiagoBobrik/llm-wiki-kit/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/SantiagoBobrik/llm-wiki-kit

Made for: Claude Code.

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 llm-wiki-kit CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/santiagobobrik/llm-wiki-kit/claude-md/github.svg)](https://agentmods.dev/instructions/santiagobobrik/llm-wiki-kit/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/santiagobobrik/llm-wiki-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/santiagobobrik/llm-wiki-kit/claude-md/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 llm-wiki-kit CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/santiagobobrik/llm-wiki-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/santiagobobrik/llm-wiki-kit/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 762 This file is loaded in full into every session.
When invoked 762 The same file — it is already loaded in full.
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 $0.00762 $0.00762
Opus 5 $0.00381 $0.00381
Sonnet 5 $0.00152 $0.00152
Haiku 4.5 $0.00076 $0.00076

Measured 12d ago against content hash f31329b18609, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

llm-wiki-kit CLAUDE.md 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 12d 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.

CLAUDE.md · 36 lines

How it starts

The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What this repo is

A distribution pack of five Claude Code skills that together implement a personal wiki pattern on top of an Obsidian vault. There is no build, no test suite, no runtime — the "code" is skill markdown files that Claude Code loads and executes. Editing this repo means editing skill prompts and the shipped contract template.

Architecture

Three layers the skills operate on in a target workspace (not this repo):

  • Raw/ — immutable source clippings (Obsidian Web Clipper output). Read-only to the LLM. New items are marked compiled: false in frontmatter; wiki-compile flips them to true after ingest.
  • Wiki/ — LLM-owned synthesized articles plus index.md (catalog) and sibling Raw/log.md (compile run history).
  • The contract — writing rules, frontmatter spec, structure. Lives as skills/wiki-init/assets/contract-template.md in this repo. wiki-init inlines it into the target's CLAUDE.md as a ## Wiki section, stripping the top # Wiki header and demoting every remaining heading one level so it nests cleanly. The runtime skills (compile, search, save, lint) then read the target's CLAUDE.md for rules — there is no separate Wiki.md at the target root.

Skill relationships:

  • wiki-init — one-shot bootstrap. Creates Raw/ + Wiki/, inlines the contract into CLAUDE.md. Idempotent; never silently overwrites an existing ## Wiki section.
  • wiki-compileRaw/Wiki/. Groups clippings by topic, enriches existing articles instead of duplicating (checks Wiki/index.md first), runs a close-check for source fidelity, updates index + log, flips compiled flag.
  • wiki-search — reads Wiki/index.md then drills into articles; returns synthesized answer with wikilink citations.
  • wiki-save — files a conversation answer into Wiki/ with origin: conversation frontmatter. Updates existing article if one matches, else creates.
  • wiki-lint — read-only audit (contradictions, unsourced claims, overloaded articles, under-used sources, AI-voice tone). Suggests, never edits.

Read the full file on GitHub · 36 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. 12d ago First seen · 36 lines · 762 tokens per session scan A f31329b18609

Subscribe to this mod's changes

llm-wiki-kit CLAUDE.md is an instructions file published in the GitHub repository SantiagoBobrik/llm-wiki-kit (10 stars, last pushed 2mo ago), licensed MIT. It adds 762 tokens to every session, about $0.0038 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 instructions, from other repositories

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,126 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens