Borrowing it
Nothing to install: this file belongs to smykla-skalski/klaudiush. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/smykla-skalski/klaudiush/main/CLAUDE.mdgit clone --depth 1 https://github.com/smykla-skalski/klaudiushWrote 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.
[](https://agentmods.dev/instructions/smykla-skalski/klaudiush/claude-md)<a href="https://agentmods.dev/instructions/smykla-skalski/klaudiush/claude-md"><img src="https://agentmods.dev/badge/instructions/smykla-skalski/klaudiush/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.
<a href="https://agentmods.dev/instructions/smykla-skalski/klaudiush/claude-md"><img src="https://agentmods.dev/badge/instructions/smykla-skalski/klaudiush/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.05328 | $0.05328 |
| Opus 5 | $0.02664 | $0.02664 |
| Sonnet 5 | $0.01066 | $0.01066 |
| Haiku 4.5 | $0.00533 | $0.00533 |
Grade A, and why
klaudiush 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 433 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for Claude Code (claude.ai/code) when working with this repository.
Project Overview
klaudiush is a validation dispatcher for Claude Code hooks. Intercepts PreToolUse events and validates commands before execution, enforcing git workflow standards and commit message conventions.
Commands
# Completion (shell completion scripts)
klaudiush completion bash # generate bash completion
klaudiush completion fish # generate fish completion
klaudiush completion zsh # generate zsh completion
klaudiush completion powershell # generate powershell completion
# Init (interactive setup wizard, creates config.toml + registers hooks)
./bin/klaudiush init # project config + hooks
./bin/klaudiush init --global # global config + hooks
./bin/klaudiush init --force # overwrite existing
./bin/klaudiush init --install-hooks # register hooks only
./bin/klaudiush init --install-hooks --global # register hooks globally
./bin/klaudiush init --install-hooks=false # config only, no hooks
# Doctor (diagnose setup and configuration)
./bin/klaudiush doctor # run all checks
./bin/klaudiush doctor --verbose # detailed output
./bin/klaudiush doctor --fix # auto-fix issues
./bin/klaudiush doctor --category binary,hook # filter by category
# Debug (inspect configuration)
./bin/klaudiush debug rules # show all rules
./bin/klaudiush debug rules --validator git.push # filter by validator
./bin/klaudiush debug exceptions # show exception config
./bin/klaudiush debug exceptions --state # include rate limit state
# Crash (crash dump management)
klaudiush debug crash list # list all crash dumps
klaudiush debug crash view <id> # view crash dump details
klaudiush debug crash clean # remove old dumps
klaudiush debug crash clean --dry-run # show what would be removed
# Audit (exception audit log management)
./bin/klaudiush audit list # list all entries
./bin/klaudiush audit list --error-code GIT019 # filter by code
./bin/klaudiush audit list --outcome allowed # filter by outcome
./bin/klaudiush audit stats # show statistics
./bin/klaudiush audit cleanup # remove old entries
# Bypass (validation when approval prompts are off)
./bin/klaudiush bypass status # show effective setting
./bin/klaudiush bypass skip --reason "spike" # stop validating in bypass modes
./bin/klaudiush bypass skip --duration 4h # time-boxed opt-out
./bin/klaudiush bypass enforce # restore the default
./bin/klaudiush bypass notify off # keep validating, hide the reminder
# Build & Install
mise run build # dev build
mise run build:prod # prod build (validates signoff)
mise run install # install to ~/.claude/hooks/dispatcher
# Testing
mise run test # all tests
mise run test:unit # unit tests only
mise run test:integration # integration tests only
mise run test:fuzz # fuzz tests (10s each)
mise run test:fuzz:git # git parser fuzz (60s)
FUZZ_TIME=5m mise run test:fuzz:git # custom duration
# Linting & Development
mise run check # lint + auto-fix
mise run lint # lint only
mise run fmt # format code
mise run deps # update dependencies
mise run verify # fmt + lint + test
mise run clean # clean artifacts
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.
- 10d ago First seen · 433 lines · 5,328 tokens per session scan A 39820a5af963
klaudiush CLAUDE.md is an instructions file published in the GitHub repository smykla-skalski/klaudiush (13 stars, last pushed yesterday), licensed MIT. It adds 5,328 tokens to every session, about $0.0266 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.
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.
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.
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).
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.
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).
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.