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-reviewgit 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-review)<a href="https://agentmods.dev/skills/tellang/triflux/tfx-review"><img src="https://agentmods.dev/badge/skills/tellang/triflux/tfx-review/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-review"><img src="https://agentmods.dev/badge/skills/tellang/triflux/tfx-review.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 | $0.00083 | $0.02393 |
| Opus 5 | $0.00042 | $0.01196 |
| Sonnet 5 | $0.00017 | $0.00479 |
| Haiku 4.5 | $0.00008 | $0.00239 |
Grade A, and why
tfx-review 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.
curl -sf http://127.0.0.1:27888/status >/dev/null && \ How it starts
The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tfx-review — Code Review (Deep by Default)
ARGUMENTS 처리: 이 스킬이
ARGUMENTS: <값>과 함께 호출되면, 해당 값을 사용자 입력으로 취급하여 워크플로우의 첫 단계 입력으로 사용한다.--quick플래그 감지 시 quick 경로로 분기.
기본값: Deep (3-CLI Consensus)
AI makes completeness near-free. 기본은 풀프라이스 딥. 빠른 피드백은
--quickopt-out.
Anti-Herding: Round 1에서 3개 CLI가 서로의 결과를 보지 않고 독립 리뷰. Consensus Only: 2개 이상 CLI가 동일 이슈를 지적한 항목만 최종 보고 → false-positive 87% 감소.
모드 분기 (첫 단계)
ARGUMENTS 에 --quick 포함 → Quick 모드 (아래 Quick 섹션).
그 외 → Deep 모드 (기본).
Deep 모드 (기본)
전제조건 프로브
진입 즉시 실행 — 10초 내 가시적 출력 보장. 빈 stdout + exit 0 금지.
(tmux -V 2>/dev/null || psmux -V 2>/dev/null) && \
curl -sf http://127.0.0.1:27888/status >/dev/null && \
codex --version 2>/dev/null && \
agy --version 2>/dev/null
Tier 판정
| Tier | 조건 | 실행 방식 |
|---|---|---|
| Tier 1 | Hub + Codex + Antigravity 전부 정상 | auto multi 3-CLI (tmux/psmux 리드면 interactive) |
| Tier 2 | Codex 또는 Antigravity 중 하나만 가용 | 가용 CLI + Claude Agent 조합 |
| Tier 3 | Hub 또는 필요 CLI 불가, 또는 claude -p one-shot |
Claude Agent only (consensus 미적용) |
IF claude -p (one-shot):
→ Tier 3
IF Hub 미응답:
→ hub-ensure 자동 재시작 시도: Bash("node ~/.claude/scripts/hub-ensure.mjs")
→ 성공 → Tier 판정 재시도
→ 실패 → Tier 3
IF Codex 없음 AND Antigravity 없음:
→ Tier 3
IF Codex 없음 OR Antigravity 없음:
→ Tier 2
ELSE:
→ Tier 1
Tier 3 진입 시 필수 출력
⚠ [Tier 3] multi 실행 환경 미충족 — single-model 모드로 실행합니다 (consensus 미적용)
누락: {missing_components}
권장: Hub, Codex CLI, Antigravity CLI 설치 후 재실행
또는 /tfx-review --quick 으로 명시적 quick 경로 사용
HARD RULES (Tier 1/2)
headless-guard가 이 규칙 위반을 자동 차단한다.
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
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 · 223 lines · 83 tokens per session scan A 252e1fa2f5b4
tfx-review is a skill published in the GitHub repository tellang/triflux (7 stars, last pushed 3d ago), licensed MIT. It adds 83 tokens to every session and 2,393 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
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.