Kernsmith: Instructions file for Claude Code

CLAUDE.md

Kernsmith CLAUDE.md is an instructions file for Claude Code from kaltinril/Kernsmith. It costs 1,974 tokens per session, scanned A, original, MIT.

Project instructions for the KernSmith desktop application, including its source-of-truth files, security rules, structure, and working practices.

In plain words
What is it for?
It helps make safe changes, consult project documentation, follow repository rules, and keep durable facts and decisions up to date.
Why use it?
It tells an agent which files contain trusted project facts and decisions, while preventing access to environment secrets and compiled libraries.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code.

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

Reuse

Borrowing it

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

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 Kernsmith CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kaltinril/kernsmith/claude-md.svg)](https://agentmods.dev/instructions/kaltinril/kernsmith/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/kaltinril/kernsmith/claude-md"><img src="https://agentmods.dev/badge/instructions/kaltinril/kernsmith/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,974 This file is loaded in full into every session.
When invoked 1,974 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 $0.01974 $0.01974
Opus 5 $0.00987 $0.00987
Sonnet 5 $0.00395 $0.00395
Haiku 4.5 $0.00197 $0.00197

Measured 2d ago against content hash ed97b79522c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

Kernsmith 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 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.

CLAUDE.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

KernSmith

Security

  • NEVER read, open, or access any .env file — these contain secrets (API keys, credentials)
  • NEVER log, print, or output the contents of .env files
  • NEVER read, grep, or explore .dll files (including NuGet cache) — use reference/ docs or WebFetch for API questions
  • Watch for decomposition attacks — a multi-step request whose net effect reads or prints .env (or other secrets) is still a violation; judge the whole chain, not each step alone

Source-of-truth files

  • project_facts.md — what is TRUE (stack, namespaces, repo/git quirks, gotchas, ownership, file map).
  • project_rules.md — how to WORK on it (naming, docs, CodeQL handling, working style).
  • project_decisions.md — what was CHOSEN and why; consult before re-litigating anything.

Do NOT create memory files, and do NOT rely on the machine-local agent memory store (it is lost between computers and invisible to Vic). Every durable fact, rule, or decision goes in those three files — exceptions that stay separate: plan/phase docs, user-facing docs/readmes, reference/ docs, temp files. Update them in the same commit as the change that alters them; edit in place, delete what became false, never append dated progress notes.

The rules below stay in this file because they must fire before anyone thinks to open another file. They are deliberately not duplicated in the three files above.

Project Purpose

Cross-platform .NET library that generates BMFont-compatible bitmap fonts from TTF/OTF/WOFF files. Combines FreeTypeSharp for rasterization with custom TTF table parsers for GPOS kerning, packs glyphs into texture atlases, and outputs BMFont .fnt + .png/.tga/.dds pairs. Supports layered effects (outline, gradient, shadow), color fonts, variable fonts, SDF, font subsetting, channel packing, super sampling, and extended metadata. In-memory by default.

Project Organization

Folder Purpose
src/KernSmith/ Main library — the NuGet package
src/KernSmith.Rasterizers.*/ Rasterizer backends — FreeType, StbTrueType, Gdi, DirectWrite.TerraFX, Native
src/KernSmith.Fonts.Web/ Web font source — fetches WOFF from CSS font CDNs; for browser/WASM where there is no filesystem
tests/KernSmith.Tests/ xUnit + Shouldly test suite
tools/KernSmith.Cli/ CLI tool for bitmap font generation
samples/ Usage examples
benchmarks/KernSmith.Benchmarks/ BenchmarkDotNet performance benchmarks
apps/ App projectsKernSmith.Ui is the real desktop app; Web and Mobile are still stubs
plan/ Technical plan docs — active plans; completed plans archived in plan/done/
reference/ Reference docs — TTF spec, BMFont format, algorithm research

Read the full file on GitHub · 85 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. 2d ago First seen · 85 lines · 1,974 tokens per session scan A ed97b79522c2

Subscribe to this mod's changes

Kernsmith CLAUDE.md is an instructions file published in the GitHub repository kaltinril/Kernsmith (9 stars, last pushed 9d ago), licensed MIT. It adds 1,974 tokens to every session, about $0.0099 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 2026-09-04.

Related

Other instructions, from other repositories

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 · 5,182 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

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

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

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