siegard-code CLAUDE.md

Repository instructions for Siegard Code, a development lab for building reusable AI agents and skills rather than a user-facing product.

In plain words
What is it for?
Use them when developing, testing, documenting, packaging, or installing the lab’s agent and skill structures.
Why use it?
They explain which folders contain published files, documentation, tests, and internal material, reducing the risk of changing or publishing the wrong files.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/zig999/siegard-code/claude-md
Clone the repo
git clone --depth 1 https://github.com/zig999/siegard-code
Per session 3,830 This file is loaded in full into every session.
When invoked 3,830 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.03830 $0.03830
Opus 5 $0.01915 $0.01915
Sonnet 5 $0.00766 $0.00766
Haiku 4.5 $0.00383 $0.00383

Measured 2d ago against content hash fa413dde9777, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

siegard-code 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 · 426 lines

How it starts

The opening of the file, as written. The whole thing — 426 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — AI FIRST AGENT LAB (v2)

Project Purpose

This project is a Claude Code agent development lab. Its sole purpose is to design, build, and refine agent and skill structures that will be reused in other projects.

Important: This repository is not a product. It is the agent infrastructure that powers other projects.


Project Structure

siegard-code/
├── dist/              # Distribution root — production artifacts (see below)
│   └── .claude/       # Copied manually into <target>/.claude/ (see Installation)
├── releases/          # Versioned install archives (siegard-dist-vX.Y.Z.zip of dist/.claude)
├── docs-en/           # End-user documentation (English) for downstream projects
├── docs/              # Internal project documentation (diagrams, flow maps)
├── extras/            # Reference specs, architecture docs, event schemas — NOT published
├── tests/             # Test suite that validates dist/ artifacts
├── skills-lock.json   # Locks external skill versions (analogous to package-lock.json)
└── assets/            # Static assets (logo, images)

Directory rules

Path Purpose Write rule
dist/ Published artifacts consumed by target projects Only complete, validated artifacts; nothing outside .claude/ (self-containment — see Rules for ./dist)
releases/ Versioned install archives of dist/.claude One zip per release tag, extraction-verified with verify_install.py before commit
docs-en/ Human-readable docs shipped with the system Update when commands/flows change
docs/ Internal diagrams and flow maps Freely editable
extras/ Reference specs and architecture docs Read-only during implementation — edit only when architecture changes
tests/ Automated validation of dist/ Must pass before promoting to dist/

Installation (manual copy)

There is no install script. Installation is a manual copy of the contents of dist/.claude/ into <target-project>/.claude/. Consequence for every artifact in dist/: it must be self-describing — provenance, version, and usage context must travel inside the copied files themselves, because no tooling runs at install time.

Read the full file on GitHub · 426 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 · 426 lines · 3,830 tokens per session scan A fa413dde9777

Subscribe to this mod's changes

siegard-code CLAUDE.md is an instructions file published in the GitHub repository zig999/siegard-code (9 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 3,830 tokens to every session, about $0.0192 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 2026-08-31.