Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/rojim666/sztucode/claude-mdgit clone --depth 1 https://github.com/rojim666/SztuCodeWrote 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/rojim666/sztucode/claude-md)<a href="https://agentmods.dev/instructions/rojim666/sztucode/claude-md"><img src="https://agentmods.dev/badge/instructions/rojim666/sztucode/claude-md.svg" alt="Measured on agentmods" 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 | $0.00286 | $0.00286 |
| Opus 5 | $0.00143 | $0.00143 |
| Sonnet 5 | $0.00057 | $0.00057 |
| Haiku 4.5 | $0.00029 | $0.00029 |
Grade A, and why
SztuCode 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 6d 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.
What it actually says
CLAUDE.md
The current product runtime is Python. The default daemon, Agent Loop, bus protocol, CLI, and evaluation runner live under py-runtime/src/sztu_code. The TypeScript chain (packages/, desktop/) remains available via npm run daemon:ts / npm run cli:ts; the desktop workbench connects to the TypeScript daemon.
Commands
npm install
npm run typecheck
npm test
npm run build
npm run build --prefix desktop
npm run docs:protocol
npm run docs:links
npm run daemon
npm run cli -- ping
Architecture
The Tauri + Vue desktop workbench and Node terminal client connect to the TypeScript daemon (npm run daemon:ts, 127.0.0.1:7438) over JSON-RPC 2.0 NDJSON; the default npm run daemon / npm run cli start the Python daemon (py-runtime/src/sztu_code, 127.0.0.1:7437). Shared TS contracts live in packages/protocol; Python bus contracts live in py-runtime/src/sztu_code/core/bus.
Keep new product behavior in Python (py-runtime/src/sztu_code). Python scripts under packages/runtime-ts/skills are isolated helpers for artifact formats whose mature libraries are Python-first.
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.
- 6d ago First seen · 24 lines · 286 tokens per session scan A 0df32b5dd075
SztuCode CLAUDE.md is an instructions file published in the GitHub repository rojim666/SztuCode (50 stars, last pushed yesterday), licensed MIT. It adds 286 tokens to every session, about $0.0014 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
delegate-skills AGENTS.md
AGENTS.md instructions for amElnagdy/delegate-skills, covering working on delegate-skills, vocabulary, conventions, before publishing a change and local claude code config.
supi CLAUDE.md
Claude Code instructions for mrclrchtr/supi, covering claude.md, development status, pi docs-first rule, documentation expectations and package layout convention.
baro AGENTS.md
AGENTS.md instructions for jigjoy-ai/baro, covering claude.md, project overview, tech stack, directory structure and build commands.
open-plan-annotator AGENTS.md
AGENTS.md instructions for ndom91/open-plan-annotator, covering open-plan-annotator: development guide, what this is, architecture, runtime distribution and key files.
copperhead AGENTS.md
AGENTS.md instructions for copperheadhq/copperhead, covering agents.md, repository overview, sources of truth, build and verification and architecture.
seektty AGENTS.md
AGENTS.md instructions for Hilbert-beinghappy/seektty: This repository ships one out-of-tree DeepSeek Harness Bundle. Harness remains the only owner of Agent, Session, model, settings, permissions, Profile, plugin, and persistence state.