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-prunegit 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-prune)<a href="https://agentmods.dev/skills/tellang/triflux/tfx-prune"><img src="https://agentmods.dev/badge/skills/tellang/triflux/tfx-prune/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-prune"><img src="https://agentmods.dev/badge/skills/tellang/triflux/tfx-prune.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 | $0.00051 | $0.02394 |
| Opus 5 | $0.00026 | $0.01197 |
| Sonnet 5 | $0.00010 | $0.00479 |
| Haiku 4.5 | $0.00005 | $0.00239 |
Grade A, and why
tfx-prune 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 10d 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tfx-prune — Tri-Verified AI Slop Remover
라우팅 정본 D8은 .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 ai-slop-cleaner 오마주. 핵심 차별점: 단일 판단이 아닌 3자 독립 감지 + 합의 기반 제거. "AI가 만든 슬롭은 AI 3명이 합의해야 슬롭이다."
HARD RULES
headless-guard가 이 규칙 위반을 자동 차단한다. 우회 불가.
codex exec직접 호출 및 deprecated Gemini CLI 직접 호출 절대 금지- Codex·Antigravity →
Bash("tfx multi --auto-attach --dashboard --assign 'cli:프롬프트:역할' --timeout 1800", run_in_background=true)만 사용 — teammate mode는 생략해auto기본값을 쓰며, foreground Bash는 하니스가 600s에 강제 종료. 결과는 task-notification 후 회수 - Claude →
Agent(run_in_background=true) - Bash + Agent를 같은 메시지에서 동시 호출하여 병렬 실행
MODEL ROLES
| CLI | 역할 | 감지 관점 |
|---|---|---|
| Claude (Opus) | 코드 품질 분석 + 합의 중재 | 설계 원칙, 코드 구조, 불필요 추상화 |
| Codex | AI 슬롭 탐지 | 구현 효율, 중복 패턴, 과잉 에러 핸들링 |
| Antigravity | 가독성 평가 | 가독성/DX, 과잉 주석, 과잉 타입 |
슬롭 카테고리
| 카테고리 | 설명 | 예시 |
|---|---|---|
| 불필요 추상화 | 단일 용도인데 인터페이스/팩토리/전략 패턴 적용 | UserFactory for 1 user type |
| 중복 코드 | 같은 로직의 반복 | 동일 validation을 3곳에 복붙 |
| 과잉 에러 핸들링 | 발생 불가능한 에러를 처리 | catch (e) { /* impossible */ } |
| 과잉 주석 | 코드가 이미 명확한데 주석 | // increment i by 1 i++ |
| 과잉 타입 | 불필요하게 복잡한 타입 정의 | 5단계 중첩 제네릭 |
| 사용되지 않는 코드 | import 했지만 사용 안 함 | dead imports, unused variables |
| 과잉 로깅 | 불필요한 console.log/debug | console.log("here") |
EXECUTION STEPS
Step 0: 슬롭 제거 범위 선택
인자 없이 호출된 경우 사용자에게 범위를 선택받는다:
1. 최근 변경 파일만 (git diff)
2. 전체 프로젝트
3. 특정 디렉토리 지정
- 1번 →
git diff HEAD로 최근 변경 파일 대상 - 2번 → 프로젝트 전체 소스 파일 대상 (대규모 주의 경고 표시)
- 3번 → 추가 AskUserQuestion으로 대상 디렉토리 경로 입력받음
파일 경로나 git diff 범위가 인자로 이미 제공된 경우 이 단계를 건너뛴다.
Step 1: 대상 파일 수집
대상 결정 우선순위:
- 파일 경로 지정 → 해당 파일만
- git diff 범위 지정 → diff에 포함된 파일
- 입력 없음 →
git diff --name-only HEAD~1로 최근 변경 파일 - "all" → 프로젝트 전체 소스 파일 (주의: 대규모)
소스 파일만 필터: .ts, .js, .mjs, .tsx, .py 등. node_modules, dist, build 제외.
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.
- 10d ago First seen · 197 lines · 51 tokens per session scan A e50470d2ccd8
tfx-prune is a skill published in the GitHub repository tellang/triflux (7 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 2,394 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
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".
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.
code-review-excellence
This skill should be used when the user asks to review a diff or pull request, write review comments, audit code quality, establish review standards, or improve how a team performs code review.
do-it-review
Use to assess requirements and implementation quality independently, or to resolve a batch of review findings.
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.