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-interviewgit 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-interview)<a href="https://agentmods.dev/skills/tellang/triflux/tfx-interview"><img src="https://agentmods.dev/badge/skills/tellang/triflux/tfx-interview.svg" alt="Measured on agentmods" 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 | $0.00052 | $0.03123 |
| Opus 5 | $0.00026 | $0.01562 |
| Sonnet 5 | $0.00010 | $0.00625 |
| Haiku 4.5 | $0.00005 | $0.00312 |
Grade A, and why
tfx-interview 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 8d 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 — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tfx-interview — Quantified Socratic Requirements Exploration
라우팅 정본 D2는 .claude/rules/tfx-routing.md를 따른다.
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.
OMC deep-interview + ouroboros 오마주. 모호성을 숫자로 측정하고 20% 미만까지 질문한다. "측정할 수 없으면 개선할 수 없다."
Antigravity 위임: 분석·점수 계산·산출물 초안은 Antigravity CLI에 위임하여 Claude 토큰을 절약한다. 위임 패턴:
Bash("TFX_CLI_MODE=antigravity bash ~/.claude/scripts/tfx-route.sh antigravity '{prompt}'")
위임 패턴
Claude와 Antigravity의 역할을 분리하여 토큰을 최적화한다.
| 담당 | 작업 |
|---|---|
| Claude | AskUserQuestion (사용자 상호작용), 최종 파일 저장 |
| Antigravity | 모호성 점수 계산, 질문 생성, 응답 분석, 산출물 초안 |
# 위임 호출 형태
Bash("TFX_CLI_MODE=antigravity bash ~/.claude/scripts/tfx-route.sh antigravity '{prompt}'")
Antigravity 실패 시 Fallback: Claude Opus가 분석을 직접 처리한다.
용도
- 구현 전 요구사항 명확화
- 모호한 요청을 정량적으로 분석하여 실행 가능한 수준으로 구체화
- 빠진 제약 조건, 성공 기준, 경계 조건을 체계적으로 발견
- 과잉 구현/과소 구현 방지
핵심: 모호성 점수 (Ambiguity Score)
요구사항의 모호성을 수학적으로 측정한다:
ambiguity = 1 - (goal × 0.40 + constraints × 0.30 + criteria × 0.30)
각 요소 (0.0 ~ 1.0):
goal — 목표 명확도. "무엇을 달성하려는가?"가 명확한가?
constraints — 제약 조건 명확도. 범위, 기술 스택, 시간, 호환성 등
criteria — 성공 기준 명확도. "어떻게 되면 완료인가?"
예시:
입력: "인증 기능 추가해"
goal = 0.5 (인증이 무슨 인증? OAuth? JWT? 세션?)
constraints = 0.2 (기술 스택? 기존 시스템 연동?)
criteria = 0.1 (테스트? 성능? 보안 수준?)
ambiguity = 1 - (0.5×0.40 + 0.2×0.30 + 0.1×0.30) = 1 - 0.29 = 0.71 (71%)
목표: ambiguity < 0.20 (20% 미만)이 될 때까지 질문 반복.
워크플로우
Step 1: 초기 모호성 평가
사용자 입력을 Antigravity에 전달하여 초기 ambiguity score를 계산한다:
# Claude → Antigravity 위임
Bash("TFX_CLI_MODE=antigravity bash ~/.claude/scripts/tfx-route.sh antigravity 'Analyze the following requirement and calculate ambiguity score. Return JSON: {goal, constraints, criteria, ambiguity, suggested_questions}: {user_input}'")
Antigravity가 반환한 JSON에서 점수를 읽어 사용자에게 표시한다:
출력 예시:
"📊 현재 모호성: 71%
- 목표: 50% 명확 (어떤 인증 방식?)
- 제약: 20% 명확 (기술 스택 미정)
- 기준: 10% 명확 (완료 조건 없음)
→ Stage 1: Clarify부터 시작합니다."
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.
- 8d ago First seen · 310 lines · 52 tokens per session scan A f6913f3175f4
tfx-interview is a skill published in the GitHub repository tellang/triflux (7 stars, last pushed 6d ago), licensed MIT. It adds 52 tokens to every session and 3,123 once invoked, about $0.0003 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
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…
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".
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.