tfx-setup

tfx-setup is a skill for Claude Code, Codex from tellang/triflux. It costs 73 tokens per session (6,227 once invoked), scanned B, original, MIT.

A first-time setup wizard for triflux, a coding-agent add-on that coordinates terminals, hooks, and related tools. It guides configuration across Windows, macOS, and Linux.

In plain words
What is it for?
Use it after installation or updates to configure triflux, check its dependencies, and set up terminal or session management for your operating system.
Why use it?
It collects setup steps that would otherwise be easy to miss, including hook registration and operating-system-specific settings.

Skill for Claude CodeCodex

Written for Claude Code and Codex: argument-hint in frontmatter, but also runs codex exec. Also seen: reads .claude/ paths; mentions CLAUDE.md; names the AskUserQuestion tool.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node scripts/codex-mcp-gateway-sync.mjs --status.

Part of the triflux plugin — 29 skills, 1 agent, 12 hooks shipped together

Good fit Use it after installation or updates to configure triflux, check its dependencies, and set up terminal or session management for your operating system.

Compare 6 skills from other repositories ↓
Install

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.

Clone the repo
git clone --depth 1 https://github.com/tellang/triflux
agentmods
npx agentmods add skills/tellang/triflux/tfx-setup

Made for: Claude Code, Codex.

Or install triflux, the plugin that ships this one along with the rest of its 29 skills, 1 agent, 12 hooks.

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.

agentmods badge for tfx-setup

README.md
[![agentmods](https://agentmods.dev/badge/skills/tellang/triflux/tfx-setup.svg)](https://agentmods.dev/skills/tellang/triflux/tfx-setup)
Your own site
<a href="https://agentmods.dev/skills/tellang/triflux/tfx-setup"><img src="https://agentmods.dev/badge/skills/tellang/triflux/tfx-setup.svg" alt="Measured on agentmods" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,227 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00073 $0.06227
Opus 5 $0.00036 $0.03113
Sonnet 5 $0.00015 $0.01245
Haiku 4.5 $0.00007 $0.00623

Measured 7d ago against content hash 039ef0efa168, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

tfx-setup 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 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.

Reads agent configuration directoriesmediumAgent snooping

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

`~/.claude/settings.json`을 Read 도구로 읽어 필수 훅이 등록되어 있는지 확인한다.
packages/triflux/skills/tfx-setup/SKILL.md · 565 lines

How it starts

The opening of the file, as written. The whole thing — 565 lines — stays where its author put it; the contents beside it link to each section on GitHub.

tfx-setup — triflux 초기 설정 위저드

설치 후 최초 1회 + 매 업데이트 후 실행 권장. tfx update 완료 후에도 이 스킬의 단계 1.5(훅 등록 확인)를 반드시 실행하여 신규/변경된 훅이 settings.json에 반영되도록 한다. 훅 우선순위 관리는 tfx-hooks 스킬의 오케스트레이터 패턴을 따른다.

OS별 동작

triflux 자체는 cross-platform (macOS / Linux / Windows) 이지만, 일부 안내·룰은 Windows 발 origin이 그대로 노출된다. 아래 표를 참고하여 macOS/Linux 사용자는 Windows 전용 항목을 skip 한다.

영역 Windows macOS · Linux
탭/패인 매니저 Windows Terminal (wt.exe) → wt-manager.mjs 경유 필수 별도 매니저 없음. hub/team/terminal-opener.mjs 의 3단계 fallback (win32→wt-manager / tmux 감지→tmux/psmux / darwin→Terminal.app) 으로 동작
psmux winget install psmux / scoop install psmux / choco install psmux / cargo install psmux Windows용 native tmux. macOS/Linux는 tmux가 primary
<psmux-wt> 룰 (CLAUDE.md / .claude/rules/tfx-psmux.md) RULE 13, 56, 8 적용 (PowerShell, wt-manager, WT layout) RULE 13, 56, 8 skip 가능. RULE 4 (Codex CLI 인자) 와 gpt55 profile policy 는 공통 적용
tfx doctor 의 WT 항목 WT: <version> 또는 WT: not found 현재 build 는 WT: not found 로 표시될 수 있음 — Windows 미설치이므로 정상. 후속 PR 에서 WT: N/A (non-Windows) 로 명시 표기 예정
PowerShell 7+ 우선 (pwsh -File 필수) zsh (macOS 기본) / bash. 인라인 명령 가능
경로 Windows 형식 (C:\Users\...) POSIX (/Users/..., $HOME)

요지:

  • mac/Linux 사용자: <psmux-wt> 섹션의 WT/PowerShell 안내는 무시. psmux 만 설치하면 tfx-multi · swarm 의 로컬 병렬은 동일하게 동작한다.
  • Windows 사용자: 기존 안내 그대로 적용.

워크플로우

Step 1: 모드 선택 (AskUserQuestion)

question: "어떤 설정 모드를 실행하시겠습니까?"
header: "모드"
options:
  - label: "전체 설정 (Recommended)"
    description: "6단계 순서 실행: 동기화 → HUD → 프로파일 → CLI → MCP → 검색 MCP"
  - label: "단계별 선택"
    description: "필요한 단계만 골라서 실행"
  - label: "현재 상태 확인"
    description: "설정 없이 진단만 수행"

doctor 인자가 있으면 바로 triflux doctor 실행.

Step 2: 전체 설정 (6단계)

각 단계를 순서대로 실행하며 결과를 보고한다.

단계 1: 파일 동기화
Bash("triflux setup")

스크립트/HUD/스킬을 ~/.claude/에 배포. 결과 표시. tfx setup 은 user-state 파일(예: macOS/Linux ~/.config/triflux/hosts.json, Windows %APPDATA%\triflux\hosts.json)을 덮어쓰지 않는다.

Read the full file on GitHub · 565 lines

Files

What ships with it

1 file 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.

  1. 7d ago First seen · 565 lines · 73 tokens per session scan B 039ef0efa168

Subscribe to this mod's changes

tfx-setup is a skill published in the GitHub repository tellang/triflux (7 stars, last pushed 4d ago), licensed MIT. It adds 73 tokens to every session and 6,227 once invoked, about $0.0004 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 2026-08-31.

Related

Other skills, from other repositories

ready

Make an unfamiliar repository agent-ready with a verify command, smoke tests, guardrails, and project notes. Use for repository setup, agentic engineering, verify commands, hooks, or allowlists; skip when verification and scope are already clear.

ohm41321/luciazero · 50 tokens

lucia-chat

Set two agent sessions talking through the Luciazero Agent Bus and watch it live in a terminal: pick the pair, open the panes, read the transcript. Use for "ให้ codex กับ claude คุยกัน" or "watch the bus".

ohm41321/luciazero · 55 tokens

handoff

Write a state capsule so the next session — or a different agent/harness — can resume unfinished work without re-deriving context. Use when a session is ending with work incomplete, when the user says "handoff", "pack up", "ส่งต่อ", "continue tomorrow", when switching between Claude Code and Codex mid-task, or when…

ohm41321/luciazero · 86 tokens

done

Run the closeout ritual before handing back non-trivial work; full verification, revert-probe honesty, independent review, and scope reporting. Use before declaring completion, opening a PR, wrapping up a change, or "ปิดงาน".

ohm41321/luciazero · 50 tokens

retro

Record durable lessons, null results, and footguns after hard work or debugging. Use when the user asks for a retro, dead ends need preserving, a task disproves an approach, or "จดบทเรียน". Keep repo knowledge separate from machine-local memory.

ohm41321/luciazero · 55 tokens

show

Visualize code structure, changes, and verification evidence in the smallest useful view. Use for connections, flows, diffs, file maps, Mermaid diagrams, evidence maps, or focused HTML; show facts and label unknowns.

ohm41321/luciazero · 47 tokens