What is worker-setup?

An onboarding workflow for setting up external coding workers, such as Codex, Gemini, Grok, and Kiro, one at a time.

Use it to inspect worker availability, install missing tools, authenticate each worker, and verify that its connection works.

It avoids trying to use a worker before its command, login, or connection is ready, while explaining possible costs before installation or paid checks.

worker-setup — Skill for Claude Code by joymin5655/Agent

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 joymin5655/Agent

Claude Code

/plugin install agent-harness-extras

Made for: Claude Code.

Or install agent-harness-extras, the plugin that ships this one along with the rest of its 10 skills, 1 agent.

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/joymin5655/agent/worker-setup/github.svg)](https://agentmods.dev/skills/joymin5655/agent/worker-setup)

Your own site

<a href="https://agentmods.dev/skills/joymin5655/agent/worker-setup"><img src="https://agentmods.dev/badge/skills/joymin5655/agent/worker-setup/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/joymin5655/agent/worker-setup"><img src="https://agentmods.dev/badge/skills/joymin5655/agent/worker-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,717 The whole file, excluding the scripts and references it only reads on demand.

Security scan D 3 findings. 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	$0.00079	$0.02717
Opus 5.5	$0.00032	$0.01087
Sonnet 5.5	$0.00016	$0.00543
Haiku 4.5	$0.00008	$0.00272

Measured 14d ago against content hash fb2607e10b7c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade D, and why

worker-setup scanned grade D with 3 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 14d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

macOS. Shell installer (`curl -fsSL https://chatgpt.com/codex/install.sh | sh`)

Reads agent configuration directoriesmediumAgent snooping

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

| config seeded | codex: `~/.codex/config.toml` exists; gemini/antigravity: `~/.agent/antigravity-tiers.json` |

Makes network callslowCapability

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

macOS. Shell installer (`curl -fsSL https://chatgpt.com/codex/install.sh | sh`)

extras/skills/worker-setup/SKILL.md · 214 lines

How it starts

The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/worker-setup

Goal

Onboard the cross-vendor worker lanes (core/infra/backends.json) one at a time: install → authenticate → verify, with an honest cost/allocation briefing up front. This skill never dispatches a review or a completion check itself — that is core/infra/call-worker.sh, consumed by /council-review and /verify-completion --second-opinion. This skill only gets a lane from absent to healthy.

Step 0 — resolve the harness root

HR="$(bash "${CLAUDE_PLUGIN_ROOT}/scripts/harness-root.sh")" || echo "worker-setup: agent-harness core (backends registry) not found — install agent-harness@agent, or set AGENT_HARNESS_ROOT to a harness checkout" >&2
test -n "$HR" && test -f "$HR/core/infra/backends.json" || echo "worker-setup: backends registry not found at ${HR:-<unresolved>}" >&2

Stop here with that guidance if the registry does not resolve. Paths below are under $HR; every command block resolves it again, because each Bash call is a fresh shell.

Step 1 — read-only status sweep (zero paid calls)

Read $HR/core/infra/backends.json live with jq, in a block that sets HR first like the one above — never hardcode the lane list, the registry is the source of truth and can grow lanes this skill has never seen. For every backend, report one row:

Column	How to get it
lane	the backend's key in `.backends`
vendor	`.backends[$lane].vendor`
cmd on PATH	`command -v` on `.backends[$lane].cmd[0]`
preflight on PATH	`command -v` on `.backends[$lane].preflight[0]`
config seeded	codex: `~/.codex/config.toml` exists; gemini/antigravity: `~/.agent/antigravity-tiers.json`
cost model	from step 2's table
tiers	keys of `.backends[$lane].tier_args`
roles served	reverse-lookup: which `.roles[*].backend` (or `.fallback`) names this lane

Also run once, read-only:

HR="$(bash "${CLAUDE_PLUGIN_ROOT}/scripts/harness-root.sh")"
[ -n "$HR" ] && python3 "$HR/core/infra/runtime-profile.py" detect --json   # empty HR: stop

Read the full file on GitHub · 214 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.

14d ago Changed · +20 lines fb2607e10b7c
16d ago Changed · +1 lines · +79 tokens per session 7b8acebdcff1
28d ago Changed · -19 lines 9b4872a5447c
29d ago Changed · +9 lines e0e7c4d8abf3
1mo ago Changed · +5 lines 2237404da8d1
2mo ago First seen · 198 lines · 0 tokens per session scan D c2263100ccbc

Subscribe to this mod's changes

worker-setup is a skill published in the GitHub repository joymin5655/Agent (2 stars, last pushed yesterday), licensed MIT. It adds 79 tokens to every session and 2,717 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it D with 3 findings (downloads and executes remote code, reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents Claude Code LLM agent-infrastructure ai-agents devtools policy-as-code

worker-setup next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
worker-setupjoymin5655/Agent	Skill	2	yesterday	MIT	D	79	Claude Code
agent-prompt-auditavibe-bot/avibe	Skill	637	yesterday	MIT	A	105	Codex
computer-useavibe-bot/avibe	Skill	637	yesterday	MIT	A	19	Claude Code, Codex
background-watch-hookavibe-bot/avibe	Skill	637	yesterday	MIT	A	32	Claude Code, Codex
use-avibe-harnessavibe-bot/avibe	Skill	637	yesterday	MIT	A	36	Claude Code, Codex
use-avibe-vaultavibe-bot/avibe	Skill	637	yesterday	MIT	A	36	Claude Code, Codex
use-show-pagesavibe-bot/avibe	Skill	637	yesterday	MIT	A	39	Claude Code, Codex

worker-setup