agentmods.dev

context-engineering CLAUDE.md

A repository instruction file for Claude Code, an AI coding assistant. It records the project's purpose, preferred working style, commands, and design details.

In plain words
What is it for?
Use it to guide Claude Code when modifying or explaining the context-engineering course materials, MCP servers, or WarnerCo Schematica application.
Why use it?
It gives the assistant project-specific guidance so its changes and responses fit the repository. It also states safety rules for running servers and limits unnecessary edits.

Instructions file

27 2mo ago A scan 4,397 tokens original MIT
View the source file timothywarner-org/context-engineering
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/timothywarner-org/context-engineering/claude-md
Clone the repo
git clone --depth 1 https://github.com/timothywarner-org/context-engineering
Per session 4,397 This file is loaded in full into every session.
When invoked 4,397 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 $0.04397 $0.04397
Opus 5 $0.02198 $0.02198
Sonnet 5 $0.00879 $0.00879
Haiku 4.5 $0.00440 $0.00440

Measured 2d ago against content hash c51cbf15b2dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

context-engineering 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 · 227 lines

How it starts

The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Working Style (Tim's preferences)

  • Working > clever. Minimal, reliable code. Skip "elegant," "extensible," "future-proof."
  • Default to ≤3-file changes for a feature. If you're touching more, justify it.
  • Operational escape hatches required for anything that runs as a server/daemon (port-killers, --kill-only, idempotent re-runs). See scripts/restart_server.py as the model.
  • Terse responses. Lead with the action; end with the verification result. Skip planning sections unless asked.
  • Absolute paths in Bash — cd between tool calls has broken parallel batches in this repo.
  • Tim is a senior engineer (MVP/MCT, 25+ years). Frame as peer-to-peer. Cite file paths and line numbers.

Project Overview

Training materials and MCP server implementations for "Context Engineering with MCP" — a 4×50min course. Flagship teaching app is WARNERCO Schematica: FastAPI + FastMCP + LangGraph that exercises all four CoALA memory tiers (Working / Episodic / Semantic / Procedural) in one codebase. Source design rationale: research_synthesis/ (Claude/ChatGPT/Gemini/Perplexity deep-research reports).

Class delivery date and audit status live in instructor memory, not here. Repo layout is discoverable via Glob — top-level: src/warnerco/backend/, labs/lab-01-hello-mcp/, docs/, instructor/, config/, research_synthesis/, .claude/.

Development Commands

WARNERCO Schematica

Python 3.13 pinned (.python-version). onnxruntime (chromadb dep) lacks 3.14 wheels — uv sync fails on 3.14 with a clear platform error.

cd src/warnerco/backend
uv sync                                    # Install dependencies
uv run uvicorn app.main:app --reload       # HTTP at http://localhost:8000
uv run warnerco-serve                      # Same, via console script
uv run warnerco-mcp                        # MCP stdio server (Claude Desktop / Code / VS Code)
uv run warnerco-restart                    # Force-kill port 8000, restart uvicorn
uv run warnerco-restart --kill-only        # Just free the port
uv run warnerco-restart --port 9000        # Use a different port

Read the full file on GitHub · 227 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 · 227 lines · 4,397 tokens per session scan A c51cbf15b2dd

Subscribe to this mod's changes

context-engineering CLAUDE.md is an instructions file published in the GitHub repository timothywarner-org/context-engineering (27 stars, last pushed 2mo ago), licensed MIT. It adds 4,397 tokens to every session, about $0.0220 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.

DatabasesLLMLearning and teachingMemory and contextai-memoryanthropichybrid-ragknowledge-graphmcp-tools
Related

Other instructions, from other repositories

remnic AGENTS.md

Instructions for joshuaswarren/remnic, covering remnic - agent guide, architecture boundaries (non-negotiable), upstream references, adapter implementation rules and openclaw compatibility window.

joshuaswarren/remnic · 31,441 tokens

sibyl CLAUDE.md

Instructions for hyperb1iss/sibyl, covering sibyl development guide, project overview, sibyl integration, always use skills and research → do → reflect cycle.

hyperb1iss/sibyl · 2,212 tokens

Dragon-Brain CLAUDE.md

Instructions for iikarus/Dragon-Brain, covering dragon brain — claude.md, the harness, audit remediation (april–may 2026, complete 2026-05-09), the lie this audit closed and the contract that matters now.

iikarus/Dragon-Brain · 6,132 tokens

vellis AGENTS.md

Instructions for volantlabs/vellis, covering agents.md, repository purpose, startup checks, installing vellis for a user and model-first component workflow.

volantlabs/vellis · 4,953 tokens

engram CLAUDE.md

Instructions for techtheist/engram, covering engram — context for claude code, hard rules (locked — don't relitigate without reason), where things go, workflows & sharp edges and now / next (keywords).

techtheist/engram · 6,983 tokens

brainlayer AGENTS.md

Instructions for EtanHey/brainlayer, covering brainlayer — a letter from etan, brainlayer agent notes (operational), review guidelines, key paths and database.

EtanHey/brainlayer · 4,406 tokens