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.
git clone --depth 1 https://github.com/YousefNabil-SOC/claude-apexWrote 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/commands/yousefnabil-soc/claude-apex/switch-project)<a href="https://agentmods.dev/commands/yousefnabil-soc/claude-apex/switch-project"><img src="https://agentmods.dev/badge/commands/yousefnabil-soc/claude-apex/switch-project/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/yousefnabil-soc/claude-apex/switch-project"><img src="https://agentmods.dev/badge/commands/yousefnabil-soc/claude-apex/switch-project.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00023 | $0.00562 |
| Opus 5 | $0.00012 | $0.00281 |
| Sonnet 5 | $0.00005 | $0.00112 |
| Haiku 4.5 | $0.00002 | $0.00056 |
Grade A, and why
switch-project 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.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/switch-project
EDIT THIS FILE — replace the example projects below with your own projects. The list here is intentionally generic so everyone starts from a clean slate.
Purpose
Quick-switch between active projects with pre-loaded context. When you say /switch-project my-webapp, Claude reads the project's CLAUDE.md and MEMORY.md, changes to its directory, and restores active-project context.
Configuration — Your Projects
Define your projects below. For each one:
- Slug: what you'll type after
/switch-project - Path: absolute path to the project folder
- Trigger: optional natural-language trigger phrase (e.g. "resume my-webapp")
- Description: one line describing the project
Example Projects (REPLACE WITH YOUR OWN)
| Slug | Path | Description |
|---|---|---|
my-webapp |
~/projects/my-webapp |
Main web application (React + Vite + Vercel) |
my-api |
~/projects/my-api |
Backend API (Node.js + Postgres) |
my-docs |
~/projects/my-docs |
Documentation site (VitePress) |
Behavior
When the user types /switch-project <slug>:
- Find the matching project in the table above
cdto its absolute path- Read
CLAUDE.mdin that directory (if present) - Read
MEMORY.mdin that directory (if present) - Read the project's
graphify-out/GRAPH_REPORT.md(if present) — restores architecture awareness - Announce: "Switched to
<slug>— ready for work on "
When the user types /switch-project with no argument:
- List all projects in the table above
- Show the current working directory
- Wait for the user to pick one
Adding a New Project
- Edit this file (
~/.claude/commands/switch-project.md) - Add a row to the table above
- Save — no restart needed
Tips
- Pick short, memorable slugs (
my-webapp, notmy-webapp-production-v2-final) - Include the tech stack in the description so Claude activates the right skills
- If a project has its own CLAUDE.md, list critical rules there, not here
- Use
trigger:natural-language phrases for when you say "resume my webapp"
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.
- 7d ago First seen · 59 lines · 23 tokens per session scan A 5c53732f2d40
switch-project is a command published in the GitHub repository YousefNabil-SOC/claude-apex (2 stars, last pushed 3mo ago), licensed MIT. It adds 23 tokens to every session and 562 once invoked, about $0.0001 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 2026-09-03.
Other commands, from other repositories
context-stats
Display context window usage and token statistics.
init-project
Initialize project with CLAUDE.md template - adaptive detection for new or existing projects.
run
Execute prompt(s) from ./prompts/ with automatic archiving - for structured prompt-based work.
help
Explain Ralph Wiggum technique and available commands.
update-counts
Update all hardcoded counts (skills, agents, marketplace repos/skills) across documentation from filesystem.
cancel-ralph
Cancel active Ralph Wiggum loop.