claudectx CLAUDE.md

claudectx CLAUDE.md is an instructions file for coding agents from foxj77/claudectx. It costs 1,034 tokens per session, scanned B, original, MIT.

A set of project instructions for Claude Code, an AI coding assistant, in a Go command-line project called claudectx. It documents the project structure, configuration profiles, data flow, and build and test commands.

In plain words
What is it for?
Use it when working on claudectx to understand profile switching, configuration storage, important packages, build steps, tests, coverage checks, and static analysis.
Why use it?
It gives the coding assistant consistent project context before it changes code. It also records the commands and package responsibilities needed to build, test, and inspect the tool.

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/foxj77/claudectx/claude-md
Clone the repo
git clone --depth 1 https://github.com/foxj77/claudectx

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 claudectx CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/foxj77/claudectx/claude-md.svg)](https://agentmods.dev/instructions/foxj77/claudectx/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/foxj77/claudectx/claude-md"><img src="https://agentmods.dev/badge/instructions/foxj77/claudectx/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,034 This file is loaded in full into every session.
When invoked 1,034 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.01034 $0.01034
Opus 5 $0.00517 $0.00517
Sonnet 5 $0.00207 $0.00207
Haiku 4.5 $0.00103 $0.00103

Measured 3d ago against content hash 705e131dd708, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

claudectx CLAUDE.md scanned grade B 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 3d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- `~/.claude/settings.json` - Active settings
CLAUDE.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 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.

OpenSSF Scorecard

Project Overview

claudectx is a Go CLI tool for fast, safe profile switching in Claude Code. It manages configuration profiles stored in ~/.claude/profiles/, enabling switching between different settings, CLAUDE.md files, and MCP servers.

Build & Test Commands

make build           # Build binary (outputs ./claudectx)
make install-user    # Install to ~/go/bin (recommended, no sudo)
make test            # Run all unit tests
make test-coverage   # Run tests with coverage
go test ./... -v     # Verbose test output
go vet ./...         # Static analysis

Architecture

Core Data Flow

main.go (CLI argument routing)
  → cmd/*.go (command implementations)
    → internal/store (profile CRUD)
      → internal/config, internal/mcpconfig, internal/profile (data structures)
        → ~/.claude/ (filesystem)

Key Packages

Package Purpose
internal/store Profile persistence, tracks current/previous profile
internal/config Settings struct (Env, Model, Permissions), JSON I/O — unknown fields are preserved transparently via extras map[string]json.RawMessage
internal/mcpconfig MCP server configs from ~/.claude.json
internal/paths Centralized path resolution for Claude files
internal/printer Colored terminal output (respects NO_COLOR)
internal/backup Timestamped backups before switching
internal/validator Settings and CLAUDE.md validation

Key Paths

  • ~/.claude/settings.json - Active settings
  • ~/.claude/CLAUDE.md - Global instructions
  • ~/.claude.json - MCP server configurations
  • ~/.claude/profiles/<name>/ - Stored profiles
  • ~/.claude/.claudectx-current - Current profile tracker

Read the full file on GitHub · 109 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. 3d ago First seen · 109 lines · 1,034 tokens per session scan B 705e131dd708

Subscribe to this mod's changes

claudectx CLAUDE.md is an instructions file published in the GitHub repository foxj77/claudectx (140 stars, last pushed 1mo ago), licensed MIT. It adds 1,034 tokens to every session, about $0.0052 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.