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-goal-clarifygit 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-goal-clarify)<a href="https://agentmods.dev/skills/tellang/triflux/tfx-goal-clarify"><img src="https://agentmods.dev/badge/skills/tellang/triflux/tfx-goal-clarify/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-goal-clarify"><img src="https://agentmods.dev/badge/skills/tellang/triflux/tfx-goal-clarify.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 | $0.00107 | $0.03948 |
| Opus 5 | $0.00053 | $0.01974 |
| Sonnet 5 | $0.00021 | $0.00790 |
| Haiku 4.5 | $0.00011 | $0.00395 |
Grade A, and why
tfx-goal-clarify 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 — 374 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tfx-goal-clarify — 자연어 → /goal 블록 변환기
tfx-interview의 슬림 fork. 인터뷰 산출물을 Action Plan 대신
/goal블록 한 덩어리로만 출력한다. 공식/goal3축(End state / Stated check / Constraints) +or stop after N turns를 강제한다.
용도
Claude Code 2.1.139+의 /goal 명령어에 넣을 프롬프트를 자연어 아이디어로부터 구조화한다. /goal은 평가자(Haiku)가 transcript만 보고 yes/no 판정하므로, 측정 불가능한 조건은 무한 루프 또는 환각 yes를 유발한다. 이 스킬은 그 함정을 회피한다.
비교:
tfx-interview: 일반 요구사항 인터뷰 → 전체 Action Plan 산출tfx-goal-clarify: /goal 블록 한 덩어리만 산출 (5분 내 완료 목표)gstack-office-hours: 제품 아이디어 단계 (코드 이전)
입력 처리
ARGUMENTS: <자연어 목표>가 들어오면 첫 입력으로 사용. 없으면 사용자에게 요청.
--tier N 플래그:
1= one-liner (3턴 이내 작업)2= standard 3-part (기본값, 10턴 이내)3= 9-section (다중 모듈/다일 작업)
워크플로우
Step 1: 분류 + 초기 ambiguity 측정
코드베이스 컨텍스트 살펴보기 (선택적):
# 사용자가 어떤 repo에서 호출했는지 확인
git rev-parse --show-toplevel 2>/dev/null
자연어 입력을 3축으로 분해:
| 축 | 질문 | 점수 (0~1) |
|---|---|---|
| End state | 완료를 무엇으로 증명? | goal |
| Check | Claude가 어떤 명령/출력으로 보여줄 수 있나? | constraints |
| Constraints | 절대 건드리면 안 될 것은? | criteria |
ambiguity = 1 - (end_state×0.4 + check×0.3 + constraints×0.3)
Gemini 위임 (tfx-interview와 동일):
Bash("bash ~/.claude/scripts/tfx-route.sh gemini '<analysis prompt>'")
Gemini 미사용 환경(m5 등 SSH 원격)에서는 Claude가 직접 채점.
Step 2: 적응형 인터뷰 (AskUserQuestion 사용, Tier별 질문 수 가변)
반드시 Claude Code 네이티브 AskUserQuestion 도구를 사용한다. 자유 텍스트 질의 금지 — 사용자가 옵션 중에서 선택하도록 구조화한다.
Tier별 필수 축:
| Tier | 핵심 축 (필수) | 보조 축 (조건부) | 질문 수 |
|---|---|---|---|
| 1 | End state, Bound | — | 1~2 |
| 2 | End state, Check, Constraints, Bound | Scope | 3~5 |
| 3 | End state, Check, Constraints, Scope, Priority, Plan, Bound | Rollback, Output artifact | 5~8 |
ambiguity < 20% 도달 시 즉시 종료 (남은 질문 스킵).
AskUserQuestion 호출 패턴 (예시)
각 축마다 다음 형태로 호출. options는 사용자 입력 기반으로 동적 생성 + 사용자가 "Other"로 직접 입력 가능.
Q1. End state (모든 Tier 필수)
{
"questions": [{
"question": "이 작업이 끝났다는 걸 어떤 단일 측정 가능한 결과로 증명하나요?",
"header": "End state",
"multiSelect": false,
"options": [
{"label": "테스트 exit code", "description": "예: pnpm test <path> exits 0"},
{"label": "패턴 카운트 0", "description": "예: rg \"legacy\" src returns 0 hits"},
{"label": "타입체크 통과", "description": "예: pnpm typecheck exits 0"},
{"label": "빌드 성공", "description": "예: pnpm build exits 0"}
]
}]
}
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 · 374 lines · 107 tokens per session scan A 4636cbfa5744
tfx-goal-clarify is a skill published in the GitHub repository tellang/triflux (7 stars, last pushed 2d ago), licensed MIT. It adds 107 tokens to every session and 3,948 once invoked, about $0.0005 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.