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/foxj77/claudectx/claude-mdgit clone --depth 1 https://github.com/foxj77/claudectxWrote 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/foxj77/claudectx/claude-md)<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>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 | $0.01034 | $0.01034 |
| Opus 5 | $0.00517 | $0.00517 |
| Sonnet 5 | $0.00207 | $0.00207 |
| Haiku 4.5 | $0.00103 | $0.00103 |
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 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.
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
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.
- 3d ago First seen · 109 lines · 1,034 tokens per session scan B 705e131dd708
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.
Other instructions, from other repositories
kglite CLAUDE.md
Instructions for kkollsga/kglite, covering kglite — claude code conventions, build & test, architecture, the boundary principle (wrappers vs core) — summary and in-memory is the core product.
adeu GEMINI.md
Gemini CLI instructions for dealfluence/adeu, covering adeu — native track changes for ai, available tools, readdocx, processdocumentbatch and applytextrevision.
MCP-Airflow-API copilot-instructions.md
Instructions for call518/MCP-Airflow-API, covering copilot instructions for mcp-airflow-api, project architecture, critical patterns, functions.py - persistent session with retry strategy and standard pattern in airflowapi.py.
openings-mcp AGENTS.md
Instructions for amikai/openings-mcp, a project described as: 💼 One MCP server to search job boards and company career sites.
metatron CLAUDE.md
Instructions for kerbelp/metatron, covering claude.md, what metatron is, tech stack (decided — not open for debate), core principle and source of truth (depends on deployment).
paper-pilot CLAUDE.md
Instructions for aytzey/paper-pilot, covering claude.md, best fit, setup, first workflow to try and claude prompt patterns.