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/tellang/trifluxnpx agentmods add skills/tellang/triflux/tfx-wtWrote 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/tellang/triflux/tfx-wt)<a href="https://agentmods.dev/skills/tellang/triflux/tfx-wt"><img src="https://agentmods.dev/badge/skills/tellang/triflux/tfx-wt/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/tellang/triflux/tfx-wt"><img src="https://agentmods.dev/badge/skills/tellang/triflux/tfx-wt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00125 | $0.02625 |
| Opus 5 | $0.00063 | $0.01313 |
| Sonnet 5 | $0.00025 | $0.00525 |
| Haiku 4.5 | $0.00013 | $0.00263 |
Grade A, and why
tfx-wt 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 9d 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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tfx-wt — Windows Terminal 자연어 조작
ARGUMENTS 처리: 이 스킬이
ARGUMENTS: <값>과 함께 호출되면, 해당 값을 사용자 입력으로 취급한다. ARGUMENTS가 비어있거나 없으면 사용자에게 의도 확인 후 적절한 action 으로 라우팅한다.
인프라: keyword-rules.json 의
wt-tab-*4 규칙이 이 스킬로 라우팅한다. 사용자는 보통 자연어로 호출 ("탭 열어줘") 하므로 의도 → action 매핑이 첫 단계.
OS 정책
이 스킬은 Windows 전용. macOS/Linux 의 탭/패인 자연어 라우팅은 본 스킬 범위 외다.
| OS | 동작 | 라우팅 |
|---|---|---|
| Windows | wt.exe 실제 호출 (wt-manager 경유). safety-guard 차단 우회 |
tfx-wt 가 담당 |
| macOS / Linux | createWtManager() 가 stub 반환 (PR #241). 모든 action no-op |
terminal-opener.mjs 가 tmux 경로로 담당 (PR #236). tfx-wt 는 사용자에게 안내만 |
분리 정신 (PR #236, #241)
| 레이어 | 역할 |
|---|---|
hub/team/wt-manager.mjs |
Windows-only (non-Windows 에서 stub). tfx-wt 가 사용 |
hub/team/terminal-opener.mjs |
Cross-platform abstraction. Windows→wt-manager, macOS/Linux→tmux |
hub/team/runtime-strategy.mjs |
psmux (Windows) 와 tmux (macOS/Linux) runtime identity 분리 유지 |
macOS 사용자가 "탭 열어"라고 했는데 본 스킬로 들어오면 잘못된 라우팅. 사용자에게 다음을 안내한 뒤 종료:
- "Windows Terminal 은 macOS 에 없습니다."
- "macOS 에서 새 탭/패인 자동 생성이 필요하면
terminal-opener.mjs의 tmux 경로를 사용하세요." - "오케스트레이션 (swarm worker 배치, dashboard) 은 자동으로 OS 분기됩니다."
wt-manager.mjs 자체가 OS-aware 이므로 스킬 코드에서 platform 분기 불필요.
의도 → action 매핑
| 자연어 입력 | action | 예시 |
|---|---|---|
| 새 탭, tab open, 탭 추가/생성/열어/띄워, 터미널 탭 | create-tab |
"새 탭 열어줘" |
| 패인 분할, pane split, 화면 나눠 | split-pane |
"패인 가로로 분할" |
| 탭 + 여러 개 동시 배치, layout, dashboard | layout |
"워커 3개 가로로 배치" |
| 탭 목록, 탭 리스트, 열린 탭, 현재 탭 | list |
"지금 탭 뭐있어" |
| 탭 닫아, 탭 종료, tab close, 탭 정리 | close |
"worker 탭 닫아" |
| 오래된 탭 정리, stale 탭, idle 탭 정리 | close-stale |
"1시간 넘은 탭 정리해" |
| 탭 이름 변경, 탭 제목 바꿔, rename | rename |
"이 탭 이름 backend 로 바꿔" |
wt + psmux 통합 패턴 (Windows 기본 사용 흐름)
triflux 의 WT triflux 프로파일은 commandline = psmux (wt-manager:319 의 ensureWtProfile). 즉 wt 의 새 탭/패인 = wt 가 컨테이너, 그 안에서 psmux 가 멀티플렉서로 도는 구조. swarm worker, dashboard, 장기 세션 모두 이 형태.
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.
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.
- 9d ago First seen · 207 lines · 125 tokens per session scan A 943a31d37f4a
tfx-wt is a skill published in the GitHub repository tellang/triflux (7 stars, last pushed yesterday), licensed MIT. It adds 125 tokens to every session and 2,625 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
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…
planning-with-files
Use this by default for non-trivial multi-step work that needs persistent planning, progress tracking, or durable notes on disk. Trigger when a task will likely span multiple tool calls, research steps, verification loops, or enough context that the plan should not live only in transient chat memory.
obsidian-kb-artifacts
Use this skill for Obsidian-native formatting and derived artifacts such as Markdown formatting, wikilinks, registry tables, canvas files, optional Bases, CLI operations, and link repair. This skill does not decide knowledge routing.
boss-briefing
Vault health check — workflow pattern analysis, profile sync, session gap recovery, persona rule proposals.
codex-hud
Show Codex workspace context with local config, git state, hooks, and project hints. Standalone mode can show an expanded snapshot; patched Codex TUI footer mode is single-line. Use when the user says "codex-hud", "show Codex HUD", "status HUD", "workspace snapshot", or asks for richer Codex context.
lucia-chat
Set two agent sessions talking through the Luciazero Agent Bus and watch it live in a terminal: pick the pair, open the windows, read the transcript. Use for "ให้ codex กับ claude คุยกัน" or "watch the bus".