agentmods.dev

llm-kasten: Instructions file for Claude Code

CLAUDE.md

llm-kasten CLAUDE.md is an instructions file for Claude Code from jordan-gibbs/llm-kasten. It costs 426 tokens per session, scanned A, original, MIT.

Repository instructions for kasten, a command-line knowledge-base manager that stores Markdown notes and uses SQLite for fast searching.

In plain words
What is it for?
Use them when developing or testing kasten, syncing notes, repairing its index, searching the knowledge base, or producing JSON for AI agents.
Why use it?
They explain the project's layout, commands, architecture, and conventions so changes fit the existing system.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions AGENTS.md; mentions Gemini CLI.

This is jordan-gibbs/llm-kasten's own configuration. It tells Claude Code how to work on llm-kasten 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-kasten configures →

not rated 5repo 3mo ago A scan 426 tokens original MIT
View source ↗ jordan-gibbs/llm-kasten
Reuse

Borrowing it

Nothing to install: this file belongs to jordan-gibbs/llm-kasten. 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/jordan-gibbs/llm-kasten/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/jordan-gibbs/llm-kasten

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-kasten CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jordan-gibbs/llm-kasten/claude-md"><img src="https://agentmods.dev/badge/instructions/jordan-gibbs/llm-kasten/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 426 This file is loaded in full into every session.
When invoked 426 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 $0.00426 $0.00426
Opus 5.5 $0.00170 $0.00170
Sonnet 5.5 $0.00085 $0.00085
Haiku 4.5 $0.00043 $0.00043

Measured 2mo ago against content hash 1ce6ab027152, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

llm-kasten 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 2mo 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 · 37 lines

What it actually says

kasten

LLM-powered CLI knowledge base manager. Markdown files with YAML frontmatter as source of truth, SQLite for fast search/indexing.

Project structure

  • src/kasten/ — main package (src layout)
  • tests/ — pytest test suite (76 tests)
  • Entry points: kasten and kas (alias)

Commands

pip install -e ".[dev]"          # Install in dev mode
python -m pytest tests/ -v       # Run tests
kasten init <path>               # Create vault (--agents claude|agents|gemini|copilot|all)
kasten sync                      # Sync files -> DB
kasten repair                    # Full rebuild + fix links + promote + indexes
kasten search <query>       # Full-text search
kasten note list --json          # JSON output for LLM agents

Architecture

  • File-first: .md files are truth, SQLite is rebuildable cache
  • Single visible dir: knowledge/ at repo root, .kasten/ hidden
  • Dual output: Every command supports --json for LLM agent consumption
  • FTS5: SQLite FTS5 for search, porter stemming + unicode + BM25 ranking
  • Sync: mtime + SHA-256 change detection, BEGIN IMMEDIATE transactions
  • Links: [[wiki-links]] parsed, resolved, backlinks computed
  • Agent docs: Auto-injects into CLAUDE.md, AGENTS.md, GEMINI.md, copilot-instructions.md

Key conventions

  • All frontmatter uses yaml.safe_load / Pydantic v2 for validation
  • Enums serialize via model_dump(mode="json")
  • UTF-8-sig encoding for reading (handles BOM)
  • Slug IDs preserve underscores (used by index pages)
  • Vault path properties: vault.notes_dir, vault.index_dir, vault.knowledge_dir
  • Per-tag index pages only generated for tags with 3+ notes
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. 2mo ago First seen · 37 lines · 426 tokens per session scan A 1ce6ab027152

Subscribe to this mod's changes

llm-kasten CLAUDE.md is an instructions file published in the GitHub repository jordan-gibbs/llm-kasten (5 stars, last pushed 3mo ago), licensed MIT. It adds 426 tokens to every session, about $0.0017 per session on Opus 5.5. 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

llm-kasten CLAUDE.md compared with instructions from other repositories

llm-kasten CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
llm-kasten CLAUDE.mdjordan-gibbs/llm-kastenInstructions file53mo agoMITA426Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode