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-hubgit 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-hub)<a href="https://agentmods.dev/skills/tellang/triflux/tfx-hub"><img src="https://agentmods.dev/badge/skills/tellang/triflux/tfx-hub/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-hub"><img src="https://agentmods.dev/badge/skills/tellang/triflux/tfx-hub.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 | $0.00084 | $0.02389 |
| Opus 5 | $0.00042 | $0.01195 |
| Sonnet 5 | $0.00017 | $0.00478 |
| Haiku 4.5 | $0.00008 | $0.00239 |
Grade A, and why
tfx-hub 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 11d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Bash("curl -s http://127.0.0.1:27888/status 2>/dev/null || echo '{\"error\":\"hub 미실행\"}'") How it starts
The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tfx-hub — MCP 메시지 버스 관리 + 개방형 작업
ARGUMENTS 처리: 이 스킬이
ARGUMENTS: <값>과 함께 호출되면, 해당 값을 사용자 입력으로 취급하여 워크플로우의 첫 단계 입력으로 사용한다. ARGUMENTS가 비어있거나 없으면 기존 절차대로 사용자에게 입력을 요청한다.
인프라: 다른 스킬이 내부적으로 사용. 직접 호출할 필요 없음. CLI 에이전트(Codex/Antigravity/Claude) 간 실시간 메시지 허브를 관리합니다. 커맨드 매칭 + fallthrough: start/stop/status에 매칭되면 즉시 실행, 매칭 안 되면 hub 도메인 컨텍스트를 활용한 범용 작업으로 처리합니다.
입력 해석 규칙
/tfx-hub start → 커맨드 매칭 → 허브 시작
/tfx-hub stop → 커맨드 매칭 → 허브 중지
/tfx-hub status → 커맨드 매칭 → 상태 확인
/tfx-hub 테스트해줘 → fallthrough → hub 관련 범용 작업으로 처리
/tfx-hub 문서 저장해 → fallthrough → hub 관련 범용 작업으로 처리
/tfx-hub 브릿지 분석해 → fallthrough → hub 관련 범용 작업으로 처리
fallthrough 규칙: 인자가 start/stop/status/--port 등 커맨드 키워드에 매칭되지 않으면, 사용자의 입력을 hub/브릿지/메시지버스 도메인의 자유형 작업으로 해석한다.
fallthrough 라우팅:
# tfx-route.sh 경유 (권장)
Bash("bash ~/.claude/scripts/tfx-route.sh {에이전트} '{hub 컨텍스트 + 작업}' {mcp_profile}")
# codex 직접 호출 시 — 반드시 exec 서브커맨드 포함
Bash("codex exec --dangerously-bypass-approvals-and-sandbox --skip-git-repo-check '{작업}'")
Bash("codex --profile gpt56_sol_xhigh exec --dangerously-bypass-approvals-and-sandbox --skip-git-repo-check '{작업}'")
# ↑ --profile은 exec 앞에, --skip-git-repo-check은 exec 뒤에
# Claude 네이티브 (탐색/검증)
Agent(subagent_type="oh-my-claudecode:explore", model="haiku", prompt="{작업}")
커맨드
start — 허브 시작
Bash("node hub/server.mjs", run_in_background=true)
- Streamable HTTP MCP 서버를
http://127.0.0.1:27888/mcp에서 시작 - SQLite WAL DB:
~/.claude/cache/tfx-hub/state.db - PID 파일:
~/.claude/cache/tfx-hub/hub.pid - 환경변수:
TFX_HUB_PORT(포트),TFX_HUB_DB(DB 경로)
stop — 허브 중지
# PID 파일에서 프로세스 ID 읽어서 종료
Bash("node -e \"
const fs = require('fs');
const path = require('path');
const pidFile = path.join(require('os').homedir(), '.claude/cache/tfx-hub/hub.pid');
if (fs.existsSync(pidFile)) {
const info = JSON.parse(fs.readFileSync(pidFile, 'utf8'));
process.kill(info.pid, 'SIGTERM');
console.log('tfx-hub 종료 (PID ' + info.pid + ')');
} else {
console.log('tfx-hub 미실행');
}
\"")
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.
- 11d ago First seen · 211 lines · 84 tokens per session scan A aef506c1cc5b
tfx-hub is a skill published in the GitHub repository tellang/triflux (7 stars, last pushed 2d ago), licensed MIT. It adds 84 tokens to every session and 2,389 once invoked, about $0.0004 per session on Opus 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 2026-08-31.
Other skills, from other repositories
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".
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.
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…
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".
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.
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.