Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/notque/vexjoy-agentnpx agentmods add skills/notque/vexjoy-agent/accountsWrote 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/skills/notque/vexjoy-agent/accounts)<a href="https://agentmods.dev/skills/notque/vexjoy-agent/accounts"><img src="https://agentmods.dev/badge/skills/notque/vexjoy-agent/accounts/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/skills/notque/vexjoy-agent/accounts"><img src="https://agentmods.dev/badge/skills/notque/vexjoy-agent/accounts.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 | $0.00032 | $0.01705 |
| Opus 5.5 | $0.00013 | $0.00682 |
| Sonnet 5.5 | $0.00006 | $0.00341 |
| Haiku 4.5 | $0.00003 | $0.00170 |
Grade B, and why
accounts 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 today.
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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
`./install.sh` installs once into `~/.claude`. Every account dir holds symlinks to `~/.claude/skills`, `~/.claude/agents`, and `~/.claude/commands`, so each skill exists once and every account sees the same set. Run `lin How it starts
The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Accounts Skill
Manages multiple Claude Code accounts using isolated CLAUDE_CONFIG_DIR directories.
One directory per account keeps auth tokens, session history, and settings separate.
Shell aliases let the user pick an account before Claude Code starts — no /logout//login needed.
Script: scripts/manage-accounts.py. Registry: ~/.claude-accounts/accounts.json.
Quick reference
| Task | Command |
|---|---|
| Add an account | python3 scripts/manage-accounts.py add <name> |
| Add with a named alias | python3 scripts/manage-accounts.py add work --alias cwork |
| List all accounts | python3 scripts/manage-accounts.py list |
| Validate all accounts | python3 scripts/manage-accounts.py check |
| Launch an account | python3 scripts/manage-accounts.py launch <name> |
Share skills, agents, commands from ~/.claude |
python3 scripts/manage-accounts.py link [<name>] |
Register toolkit hooks in every account's settings.json |
./install.sh (vexinstall apply; see docs/installer-layout.md) |
| Install/update aliases | python3 scripts/manage-accounts.py install-aliases |
| Preview alias changes | python3 scripts/manage-accounts.py install-aliases --dry-run |
| Remove an account | python3 scripts/manage-accounts.py remove <name> |
Setup flow for 10+ accounts
1. Add accounts
python3 scripts/manage-accounts.py add work --alias cwork
python3 scripts/manage-accounts.py add personal --alias cpersonal
python3 scripts/manage-accounts.py add max1 --alias cm1
# … repeat for as many accounts as needed
Use named aliases (cwork, cpersonal) rather than sequential ones (c1, c2) — named aliases are self-documenting and you won't need list to remember which is which.
Each add creates ~/.claude-accounts/<name>/, assigns the alias, installs aliases into your shell config, and links the account's skills/, agents/, and commands/ to ~/.claude.
How the toolkit reaches every account
./install.sh installs once into ~/.claude. Every account dir holds symlinks to ~/.claude/skills, ~/.claude/agents, and ~/.claude/commands, so each skill exists once and every account sees the same set. Run link (no name means all accounts) to repair an account made before this, or one where Claude Code created its own skills/ dir. link moves non-conflicting content, such as skills/synced/<account-id>/, into ~/.claude first. It stops and reports on a real conflict.
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.
- today Changed · +3 lines 99c920e486ce
- 20d ago First seen · 155 lines · 32 tokens per session scan B 2cfed1ae2969
accounts is a skill published in the GitHub repository notque/vexjoy-agent (442 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 1,705 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-27.
Other skills, from other repositories
hourly-rate-time
A time-management method based on assigning a high personal value to each hour. It treats time as a limited resource and uses that value to decide which tasks to do, outsource, or skip.
screen-detox
A habit-change framework for reducing non-work screen use such as social media, short videos, games, and endless scrolling.
happiness-skill
A Chinese-language guide to happiness based on reducing unmet wants, focusing on the present, and treating happiness as a trainable skill.
monkey-mind-meditation
A meditation and reflection guide for a busy or anxious mind. It treats recurring thoughts as something to observe and examine, while noting that acute serious mental-health problems need professional care.
high-output-management
Manage for output using Grove's "High Output Management": a manager's output is their organization's output, raised by high-leverage activities. Use when the user mentions "high output management", "managerial leverage", "one-on-ones", "1:1 agenda", "OKRs", "performance review", "task-relevant maturity", "delegation"…
37signals-way
Build lean, opinionated products using the 37signals philosophy from "Getting Real", "Rework", and "Shape Up". Use when the user mentions "Getting Real", "Rework", "Shape Up", "37signals", "Basecamp method", "six-week cycles", "fixed time variable scope", "appetite vs estimates", "betting table", "breadboarding", "fat…