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/zig999/siegard-code/claude-mdgit clone --depth 1 https://github.com/zig999/siegard-codeWhat 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 | $0.03830 | $0.03830 |
| Opus 5 | $0.01915 | $0.01915 |
| Sonnet 5 | $0.00766 | $0.00766 |
| Haiku 4.5 | $0.00383 | $0.00383 |
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.
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.
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.
- 2d ago First seen · 426 lines · 3,830 tokens per session scan A fa413dde9777
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.
Other instructions, from other repositories
context-engineering AGENTS.md
Instructions for fending/context-engineering, covering agents.md, what this project is, structure, standards and navigation.
context-engineering CLAUDE.md
Instructions for fending/context-engineering, a project described as: Context engineering patterns and templates for AI coding agents. CLAUDE.md / AGENTS.md examples from single-file through agent teams with Jira integration.
langgraph AGENTS.md
Instructions for langchain-ai/langgraph, covering agents instructions, corridor security analysis, libraries and dependency map.
hatch3r CLAUDE.md
Instructions for hatch3r/hatch3r, covering hatch3r — development instructions, architecture, development commands, two-axis pillar framework (2.0.0) and orchestrator self-discipline (bypass protection).
aeon CLAUDE.md
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
ken CLAUDE.md
Instructions for townsendmerino/ken, covering claude.md, what this is, repository ownership (read this first), commands and embedding parity & golden fixtures (now in aikit).