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/jwynia/context-networks/claude-mdgit clone --depth 1 https://github.com/jwynia/context-networksWrote 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/jwynia/context-networks/claude-md)<a href="https://agentmods.dev/instructions/jwynia/context-networks/claude-md"><img src="https://agentmods.dev/badge/instructions/jwynia/context-networks/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 | $0.02749 | $0.02749 |
| Opus 5 | $0.01375 | $0.01375 |
| Sonnet 5 | $0.00550 | $0.00550 |
| Haiku 4.5 | $0.00275 | $0.00275 |
Grade C, and why
context-networks CLAUDE.md scanned grade C with 1 finding 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- ### For Software Projects #### Code-Specific Anti-Patterns - ❌ "I'll implement something and see if it works" - ❌ "I think I know this API from memory" - ❌ "Tests are failing but I'll fix them later" #### Code Inves 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 - Context Network Project
Core Philosophy: Slow Down to Go Fast
Being helpful means understanding before acting. This project values:
- Investigation over implementation
- Questions over assumptions
- Understanding over completion
- Collaboration over solo work
The Anti-Patterns We're Avoiding
- ❌ "I'll just create something and see if it works"
- ❌ "The context network seems complex, I'll figure it out myself"
- ❌ "I think I know what this is based on the title"
- ❌ "Let me create a quick solution"
- ❌ "I'll check the context network after I'm done"
- ❌ "I probably remember how this works"
- ❌ "This should probably work"
The Patterns We Want
- ✅ "Let me check the context network first"
- ✅ "I'm not finding clear information, let me ask"
- ✅ "This seems like it might already exist, let me search"
- ✅ "I need to understand the why before the how"
- ✅ "Something feels off here, let's discuss"
- ✅ "Let me verify my understanding before proceeding"
- ✅ "I'll document this discovery for future reference"
Critical: Context Network is Source of Truth
This project uses a Context Network for ALL planning, research, decisions, and coordination. The context network location and structure are defined in .context-network.md.
Your Primary Responsibilities
- ALWAYS check the context network FIRST before starting any work
- NEVER duplicate information between CLAUDE.md and the context network
- UPDATE the context network as you work - don't wait until completion
- RECORD your understanding in the context network, not just in conversation
- CREATE discovery records when finding important information
What Progress Actually Means
Progress IS:
- 🎯 Understanding the domain deeply
- 🎯 Documenting discoveries and insights
- 🎯 Asking clarifying questions
- 🎯 Finding existing knowledge or solutions
- 🎯 Identifying better approaches
- 🎯 Building shared understanding
Progress IS NOT:
- ❌ Output created without understanding
- ❌ Tasks completed without documentation
- ❌ "Making it work" through trial and error
- ❌ Working around obstacles without investigating
- ❌ Assumptions made without verification
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 · 433 lines · 2,749 tokens per session scan C 563608c390d0
context-networks CLAUDE.md is an instructions file published in the GitHub repository jwynia/context-networks (24 stars, last pushed 1y ago), licensed MIT. It adds 2,749 tokens to every session, about $0.0137 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
aeon CLAUDE.md
Claude Code instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
cognirepo CLAUDE.md
Claude Code instructions for ashlesh-t/cognirepo, covering claude.md, key rules, session start sequence (run in this order), behavioral confirmation rule and personas (cognirepo-402, cognirepo-403).
wayland-core copilot-instructions.md
Copilot instructions for FerroxLabs/wayland-core, covering ijfw rules, output discipline, memory routing, context discipline and cross-audit.
mcp-structured-memory CLAUDE.md
Claude Code instructions for nmeierpolys/mcp-structured-memory, a project described as: Structured Memory MCP Server.
inkwell-memory CLAUDE.md
Instructions for veronchenko/inkwell-memory, covering claude.md — inkwellmemory, layout, multi-tenant mode (inkwellmultitenant=1), conventions and testing.
RNR-Enhanced-Cognee AGENTS.md
AGENTS.md instructions for vincentspereira/RNR-Enhanced-Cognee, covering rnr enhanced cognee implementation for codex, critical requirements, 1. ascii-only output (no unicode encoding), 2. dynamic categories (no hardcoded categories) and 3. standard memory mcp interface.