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-researchgit 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-research)<a href="https://agentmods.dev/skills/tellang/triflux/tfx-research"><img src="https://agentmods.dev/badge/skills/tellang/triflux/tfx-research/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-research"><img src="https://agentmods.dev/badge/skills/tellang/triflux/tfx-research.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 | $0.00149 | $0.02284 |
| Opus 5 | $0.00075 | $0.01142 |
| Sonnet 5 | $0.00030 | $0.00457 |
| Haiku 4.5 | $0.00015 | $0.00228 |
Grade A, and why
tfx-research 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 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.
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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tfx-research — Web Research (Deep by Default)
ARGUMENTS 처리:
--quick→ Quick.--auto→ Auto. 그 외 → Deep (기본).
AI makes completeness near-free. 기본은 Claude(Exa/학술) + Codex(Brave/실용) 2-CLI 멀티소스 교차검증 합의 (Antigravity/Tavily는 agy --print idle 미도달 행으로 Deep 제외; Quick 단일 검색만 유지). 빠른 단일 Google Search 는
--quick. 자율 쿼리생성+구조화 보고서 는--auto.
모드 분기
| 플래그 | 모드 | 특징 |
|---|---|---|
| (없음) | Deep (기본) | 2-CLI 멀티소스 교차검증, consensus score |
--quick |
Quick | Antigravity 단일 Google Search |
--auto |
Auto | 자율 쿼리생성(3-5개) + 검색 + 구조화 보고서 |
Deep 모드 (기본)
HARD RULES
codex exec직접 호출 및 deprecated Gemini CLI 직접 호출 금지- Codex/Antigravity →
Bash("tfx multi ...")만 - Claude →
Agent(run_in_background=true) - Bash + Agent 동시 호출
모델/소스 역할
| CLI | MCP | 관점 |
|---|---|---|
| Claude | Exa (neural semantic) | 학술/기술 깊이, 공식 문서, 벤치마크 |
| Codex | Brave Search | 실용/구현/산업 사례 |
Depth 모드 (--depth 플래그)
| 모드 | 서브쿼리 | 소스/쿼리 | 라운드 | 토큰 | 시간 |
|---|---|---|---|---|---|
| quick | 3 | 2 | 1 | ~20K | 2-3분 |
| standard | 5 | 3 | 1-2 | ~40K | 5-8분 (기본) |
| deep | 8-10 | 5 | 2-3 | ~80K | 10-15분 |
EXECUTION
Pre-Phase: Depth 선택
--depth 미지정 시 AskUserQuestion.
Step 1: 주제 분석 및 쿼리 분해 (Claude Opus)
- depth 에 따른 서브쿼리 생성
- 각 쿼리에 관점(학술/실용/DX) 매핑
Step 2: 2-CLI 독립 병렬 검색 (Anti-Herding) — Bash + Agent 동시 호출
Agent (Claude + Exa):
Agent(
subagent_type="claude",
model="opus",
run_in_background=true,
prompt="서브쿼리를 Exa web_search_exa 로 검색. 서브쿼리: {sub_queries}. 관점: 학술/기술. category='research paper' 우선, highlights=true, numResults=5. 각 결과 제목/URL/핵심 추출."
)
Bash (Codex + Brave): (Antigravity/agy 제외 — agy --print 는 무거운 리서치에서 idle 미도달 시 5분 행; route 에서 --print-timeout 180s 로 bound)
Bash("tfx multi --auto-attach --dashboard \
--assign 'codex:서브쿼리를 Brave Search 로 검색. 서브쿼리: {sub_queries}. 관점: 실용/산업. brave_web_search + brave_news_search, freshness=pw. 각 쿼리 상위 5개 구조화.:researcher' \
--timeout 1800", run_in_background=true)
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 · 214 lines · 149 tokens per session scan A d634f9fc653e
tfx-research is a skill published in the GitHub repository tellang/triflux (7 stars, last pushed 2d ago), licensed MIT. It adds 149 tokens to every session and 2,284 once invoked, about $0.0007 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
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.