context-router: Instructions file for Claude Code

CLAUDE.md

context-router CLAUDE.md is an instructions file for Claude Code from jiayong1008/context-router. It costs 685 tokens per session, scanned A, original, MIT.

A set of instructions for organizing an AI assistant’s notes across multiple projects. It defines which files to read, where rules and project facts belong, and how to route requests to the right project context.

In plain words
What is it for?
Use it to manage a personal project vault with shared memory, project-specific context files, and a routing map for finding the right information.
Why use it?
It prevents project information from being scattered or mixed together. It also gives the assistant a consistent way to remember facts and handle requests when no project matches.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is jiayong1008/context-router's own configuration. It tells Claude Code how to work on context-router itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything context-router configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jiayong1008/context-router. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/jiayong1008/context-router/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/jiayong1008/context-router

Made for: Claude Code.

Wrote 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.

agentmods badge for context-router CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jiayong1008/context-router/claude-md.svg)](https://agentmods.dev/instructions/jiayong1008/context-router/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jiayong1008/context-router/claude-md"><img src="https://agentmods.dev/badge/instructions/jiayong1008/context-router/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 685 This file is loaded in full into every session.
When invoked 685 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00685 $0.00685
Opus 5 $0.00342 $0.00342
Sonnet 5 $0.00137 $0.00137
Haiku 4.5 $0.00068 $0.00068

Measured 7d ago against content hash 0fbf9de64c5d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

context-router 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 7d 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 · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

The instruction system for this vault. Read this first, every session.

How this works

  • At session start: read MEMORY.md silently. Be informed by it, don't announce it.
  • Before working on a project: read that project's _CONTEXT.md first. Find it in the routing map below.
  • When I say "remember this": write it to the right file immediately, then confirm which file.
  • If the routing map has no match: ask me rather than reading the whole vault.

Where things go

If it... Goes in...
Is a rule ("always do X") CLAUDE.md (this file)
Is a project fact or status ProjectFolder/_CONTEXT.md
Is true across everything MEMORY.md

Keep MEMORY.md short. It loads every session. Detail belongs in _CONTEXT.md, not there.

Routing map

Read the project's _CONTEXT.md when I mention any of these.

Project Trigger words Context file

Empty until setup fills it in — see 01 START HERE (give this to your AI).md. Trigger words should be whatever you'd actually type in a rush: short names, client names, teammate names, product names, and shorthand you use often.

Creating a new project

When I mention something that clearly needs its own folder, do all three, in order, without asking permission — then confirm:

  1. Create ProjectName/_CONTEXT.md from _TEMPLATE_CONTEXT.md. Fill what you know; use unknown — ask me for gaps.
  2. Add a row to the routing map above.
  3. Add one line to MEMORY.md under Active projects.

Updating

After any session where something meaningful changed — status, a decision, a new person, a finished task:

  • Update that project's _CONTEXT.md.
  • If it's a fact that spans projects (a new person, a new company), also add it to MEMORY.md.
  • Don't put project detail in MEMORY.md. Only cross-project facts go there.

Read the full file on GitHub · 73 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. 7d ago First seen · 73 lines · 685 tokens per session scan A 0fbf9de64c5d

Subscribe to this mod's changes

context-router CLAUDE.md is an instructions file published in the GitHub repository jiayong1008/context-router (2 stars, last pushed 11d ago), licensed MIT. It adds 685 tokens to every session, about $0.0034 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.

Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens