Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add tellang/triflux --skill tfx-remotegit clone --depth 1 https://github.com/tellang/trifluxWrote 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-remote)<a href="https://agentmods.dev/skills/tellang/triflux/tfx-remote"><img src="https://agentmods.dev/badge/skills/tellang/triflux/tfx-remote/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-remote"><img src="https://agentmods.dev/badge/skills/tellang/triflux/tfx-remote.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 | $0.00071 | $0.01097 |
| Opus 5 | $0.00036 | $0.00549 |
| Sonnet 5 | $0.00014 | $0.00219 |
| Haiku 4.5 | $0.00007 | $0.00110 |
Grade A, and why
tfx-remote 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tfx-remote — remote consolidated entrypoint
tfx-remote는 신규 원격 엔진이 아니라 기존 tfx-remote-setup + tfx-remote-spawn
표면을 한 명령군으로 축소한 통합 진입점이다.
Public subcommands
| Subcommand | 역할 | legacy 매핑 |
|---|---|---|
setup |
hosts 등록/편집/진단/probe-all | tfx-remote-setup |
spawn <host> [prompt] |
원격/로컬 세션 생성 | tfx-remote-spawn |
list |
활성 세션 목록 | tfx-remote-spawn --list |
attach <session> |
세션 재부착 | tfx-remote-spawn --attach |
send <session> "<msg>" |
세션에 후속 프롬프트 전송 | tfx-remote-spawn --send |
| `resume <session | host | recent>` |
kill <session> |
세션 종료 | legacy kill 동작 공식 승격 |
probe <host> |
SSH/Tailscale/Claude 연결 체크 | tfx-remote-setup / tfx-remote-spawn --probe |
capture / wait는 Phase 4b public consolidation 대상이 아니다.
필요하면 legacy passthrough로만 유지한다.
Dispatch contract
tfx-remote setup
기존 tfx-remote-setup 플로우를 그대로 사용한다.
setupsetup --addsetup --editsetup --probe-allsetup --diagnose
hosts.json 은 user-state 경로 한 곳만 읽고 쓴다.
- macOS/Linux:
~/.config/triflux/hosts.json - Windows:
%APPDATA%\triflux\hosts.json
기존 references/hosts.json 및 source/packages/global 3곳 fan-out 단계는 더 이상 사용하지 않는다.
첫 실행 시 legacy references/hosts.json 이 발견되면 lazy auto-migration으로 user-state 경로에 자동 이동된다.
tfx-remote spawn
기존 tfx-remote-spawn 플로우를 사용하되 아래 preflight를 먼저 수행한다.
- user-state
hosts.json존재 확인 - 호스트명/alias 해석
- probe TTL 확인
- SSH 실패 시
setup diagnose또는setup edit복귀 경로 제시
preflight 실패 시 중단만 하지 말고 아래 중 하나로 복귀시킨다.
tfx-remote setup --addtfx-remote setup --edittfx-remote setup --diagnosetfx-remote probe <host>
tfx-remote resume
우선순위는 아래와 같다.
- 세션명이 주어지면 해당 세션 attach/복구
- 호스트명이 주어지면 해당 호스트의 최근 세션 탐색
recent또는 생략이면 최근 세션 우선, 없으면default_host기준 새 spawn
tfx-remote kill
공식 public subcommand다. 세션 종료 전에 psmux/WT 정리 규칙은
.claude/rules/tfx-psmux.md의 detach-first 정책을 따른다.
hosts.json contract
신규 코드는 가능하면 hub/lib/hosts-compat.mjs를 기준으로 해석한다.
저장 위치는 macOS/Linux ~/.config/triflux/hosts.json, Windows %APPDATA%\triflux\hosts.json 이다.
- v1 legacy 필드 유지:
os,ssh_user,tailscale.ip,tailscale.dns,capabilities - v2 additive 필드 허용:
ssh.user,capabilities_v2,last_probe
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 · 91 lines · 71 tokens per session scan A 123788f08d7f
tfx-remote is a skill published in the GitHub repository tellang/triflux (7 stars, last pushed today), licensed MIT. It adds 71 tokens to every session and 1,097 once invoked, about $0.0004 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.
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.