kglite: Instructions file for Claude Code

CLAUDE.md

kglite CLAUDE.md is an instructions file for Claude Code from kkollsga/kglite. It costs 13,278 tokens per session, scanned A, original, MIT.

Repository instructions for KGLite, including rules for generated agent files, Rust-and-Python development, testing, linting, and the project’s core design boundary.

In plain words
What is it for?
Use them when building, linting, testing, or editing KGLite. They cover commands such as the test targets and the managed Python environment.
Why use it?
They give coding agents the project-specific rules needed to change the correct source files and run the intended checks.

Instructions file for Claude Code

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

This is kkollsga/kglite's own configuration. It tells Claude Code how to work on kglite 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 kglite configures →

Reuse

Borrowing it

Nothing to install: this file belongs to kkollsga/kglite. 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/kkollsga/kglite/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/kkollsga/kglite

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 kglite CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kkollsga/kglite/claude-md.svg)](https://agentmods.dev/instructions/kkollsga/kglite/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/kkollsga/kglite/claude-md"><img src="https://agentmods.dev/badge/instructions/kkollsga/kglite/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 13,278 This file is loaded in full into every session.
When invoked 13,278 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 $0.13278 $0.13278
Opus 5 $0.06639 $0.06639
Sonnet 5 $0.02656 $0.02656
Haiku 4.5 $0.01328 $0.01328

Measured yesterday against content hash fa466290db92, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

kglite 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 yesterday.

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 · 724 lines

How it starts

The opening of the file, as written. The whole thing — 724 lines — stays where its author put it; the contents beside it link to each section on GitHub.

KGLite — Claude Code Conventions

Authority: CLAUDE.md is the authority this repo's agent instructions are regenerated from; AGENTS.md and .agents/ are generated adapters (and .claude/skills/ is the authority for .agents/skills/). Edit the authority and regenerate in the same action — never edit an adapter.

Doctrine adoption

Follow ../doctrine/learn-from-us.md → Doctrine sync procedure at planning or release entry. Versioned corrections apply to KGLite even when made in doctrine first. Merge into the declared authority and regenerate adapters; preserve local improvements. A missing marker requires an adoption audit. Planned/deferred work does not advance dev-docs/.doctrine-synced. Snapshotting never performs sync.

Build & test

uv venv .venv                # one-time environment creation
uv run --no-sync maturin develop  # fast dev install when Python tests need current Rust code
make gate                    # fast format/static + docs-facts checkpoint
make lint                    # fast format/static lint (no build, metadata walk, or imports)
make test-mcp                # package-scoped tests; also test-core / test-cli

The repo .venv is owned by uv. For direct Python or maturin commands, use uv run --no-sync …; do not activate the environment manually and do not use bare uv run, which may sync dependencies and rebuild the editable project before running the requested command. This repository does not track uv.lock: provision with uv venv and install dependencies explicitly with uv pip install --python .venv/bin/python …. Make targets already select .venv themselves.

Build the smallest touched surface. This is a virtual workspace, so bare cargo build --lib builds every library member—including kglite-py—and then maturin recompiles a different python-extension feature/crate-type variant. Do not use that pair as a generic gate. Select one path:

  • Rust engine → make test-core or a narrower cargo test -p kglite <filter>.
  • MCP server → make test-mcp or a narrower package test filter.
  • CLI → make test-cli plus only matching interface tests.
  • Python wrapper/core test that does not exercise bundled commands → run uv run --no-sync maturin develop --no-default-features --features abi3,python-extension directly; do not pre-build the workspace.
  • MCP/CLI bridge or final packaged-contract gate → run the full default debug extension once with uv run --no-sync maturin develop (or make dev).

Read the full file on GitHub · 724 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. yesterday Changed · +8 lines · +53 tokens per session fa466290db92
  2. 4d ago Changed · +19 lines · +316 tokens per session 5c64f1561209
  3. 8d ago First seen · 697 lines · 12,909 tokens per session scan A a8b679f5d679

Subscribe to this mod's changes

kglite CLAUDE.md is an instructions file published in the GitHub repository kkollsga/kglite (38 stars, last pushed today), licensed MIT. It adds 13,278 tokens to every session, about $0.0664 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 instructions, from other repositories

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

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

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

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 · 7,104 tokens