What is setup-aliases?

A setup procedure for managing VibeProxy aliases in Claude Code. It discovers available backends, guides you through selecting them, updates its own configuration entries, and validates or rolls back changes if needed.

It helps set up, reset, or audit aliases for Codex, Copilot, Antigravity, Gemini, Qwen, and Z.AI GLM, including discovery, validation, restart checks, and rollback after a failed change.

It reduces the risk of breaking unrelated shell aliases or configuration while setting up model backends.

setup-aliases — Skill for Claude Code by LeeJuOh/claude-code-zero

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add LeeJuOh/claude-code-zero

Claude Code

/plugin install vibeproxy-kit

Made for: Claude Code.

Or install vibeproxy-kit, the plugin that ships this one along with the rest of its 1 skill.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/leejuoh/claude-code-zero/setup-aliases/github.svg)](https://agentmods.dev/skills/leejuoh/claude-code-zero/setup-aliases)

Your own site

<a href="https://agentmods.dev/skills/leejuoh/claude-code-zero/setup-aliases"><img src="https://agentmods.dev/badge/skills/leejuoh/claude-code-zero/setup-aliases/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/leejuoh/claude-code-zero/setup-aliases"><img src="https://agentmods.dev/badge/skills/leejuoh/claude-code-zero/setup-aliases.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 6,395 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00059	$0.06395
Opus 5.5	$0.00024	$0.02558
Sonnet 5.5	$0.00012	$0.01279
Haiku 4.5	$0.00006	$0.00639

Measured 1mo ago against content hash 7d49522d656c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

setup-aliases scanned grade A 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 1mo ago.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/discover.sh, scripts/probe_backend.sh, scripts/verify_probe.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Bash(curl *)

plugins/vibeproxy-kit/skills/setup-aliases/SKILL.md · 318 lines

How it starts

The opening of the file, as written. The whole thing — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.

setup-aliases

State-aware orchestration for VibeProxy aliases. This skill owns exactly two surfaces:

the vibeproxy-kit managed block in ~/.zshrc
the oauth-model-alias entries in ~/.cli-proxy-api/config.yaml that it created

Everything else — unrelated YAML keys, unrelated shell aliases, user-authored alias entries — is preserved. The skill coordinates discovery, a guided per-backend probe cycle, writes, a VibeProxy restart gate, live validation, and transactional rollback on failure.

All five scripts in ${CLAUDE_PLUGIN_ROOT}/skills/setup-aliases/scripts/ emit JSON to stdout. Your job is to chain them together, surface decisions to the user via AskUserQuestion, and persist state to ${CLAUDE_PLUGIN_DATA}/config.json before any write.

Phase 1 — Discover

Run the read-only inspector and parse its JSON:

bash ${CLAUDE_PLUGIN_ROOT}/skills/setup-aliases/scripts/discover.sh > /tmp/vibeproxy_discover.json

Then read /tmp/vibeproxy_discover.json. Key fields:

vibeproxy_installed, vibeproxy_reachable — see Onboarding gates below if either is false
user_overlay_exists, state_file_present — determines whether we are first-run or rerun
authenticated_backends — array of {token, config_key, display_name, auth_files}; see Onboarding gates below if empty or missing backends the user wants
claude_code_channel — {connected, account_count}; see Claude Code channel note below
managed_shell_aliases, managed_model_aliases, managed_payload_overrides, shortcut_shell_aliases — what the skill currently owns
backend_catalogs, partial_probe — cached probe results and any aborted probe cycle
conflicts — pre-existing cc-* entries that are not tracked in state (potential clashes); includes manual-shell-alias, manual-config-alias:<channel>, and manual-payload-override:<protocol> sources

Present a compact summary back to the user (do not dump raw JSON):

VibeProxy: installed ✓ | reachable ✓
Authenticated backends: codex, copilot, gravity, gemini (4/4)
Claude Code channel: not connected
Currently managed: 3 model aliases, 4 shell aliases, 1 shortcut
Manual conflicts detected: 0
State file: present (last probe 2 days ago)

Read the full file on GitHub · 318 lines

Files

What ships with it

8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

1mo ago First seen · 318 lines · 59 tokens per session scan A 7d49522d656c

Subscribe to this mod's changes

setup-aliases is a skill published in the GitHub repository LeeJuOh/claude-code-zero (52 stars, last pushed 3d ago), licensed MIT. It adds 59 tokens to every session and 6,395 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude Code LLM ai-agents anthropic claude developer-tools

setup-aliases

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Makes network callslowCapability

How it starts

setup-aliases

Phase 1 — Discover

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

dcf-model

mle-workflow

autonomous-loops

ascii-video

grounded-citations

hermes-agent-skill-authoring