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-plangit 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-plan)<a href="https://agentmods.dev/skills/tellang/triflux/tfx-plan"><img src="https://agentmods.dev/badge/skills/tellang/triflux/tfx-plan/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-plan"><img src="https://agentmods.dev/badge/skills/tellang/triflux/tfx-plan.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 | $0.00068 | $0.01926 |
| Opus 5 | $0.00034 | $0.00963 |
| Sonnet 5 | $0.00014 | $0.00385 |
| Haiku 4.5 | $0.00007 | $0.00193 |
Grade A, and why
tfx-plan 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 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.
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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tfx-plan — Implementation Plan (Deep by Default)
ARGUMENTS 처리:
--quick→ Quick 모드. 그 외 → Deep 모드 (기본).
AI makes completeness near-free. 기본은 Opus 4.6(Planner) + Codex(Architect) + Claude Opus(Critic) 합의. Antigravity는
agy --printstdin 경로가 단순 프롬프트에서만 검증됐으므로, schema-driven critic에는 쓰지 않고--quickfreeform 보조로만 사용한다.
모드 분기
--quick → Quick 모드 (Antigravity freeform 위임).
그 외 → Deep 모드 (기본, Opus+Codex+Claude critic 합의 + 교차 검토).
Deep 모드 (기본)
전제조건 프로브 및 Tier Degradation
curl -sf http://127.0.0.1:27888/status >/dev/null && \
codex --version 2>/dev/null && \
agy --version 2>/dev/null
| Tier | 조건 | 실행 |
|---|---|---|
| Tier 1 | Hub + 필요 CLI 전부 정상 | auto multi 3-Model (tmux/psmux 리드면 interactive) |
| Tier 2 | 일부 CLI | 가용 + Claude Agent |
| Tier 3 | Hub 또는 필요 CLI 불가 | Claude Agent only |
Tier 3:
⚠ [Tier 3] 환경 미충족 (consensus 미적용)
누락: {missing} | 또는 /tfx-plan --quick
HARD RULES
codex exec직접 호출 및 deprecated Gemini CLI 직접 호출 금지- Codex/Antigravity →
Bash("tfx multi --assign ...")만. teammate mode는 생략해auto기본값을 쓴다. - Claude →
Agent(run_in_background=true) - Bash + Agent 동시 호출
- deprecated Gemini CLI 또는 legacy Gemini assign 금지. Antigravity는
antigravity:/agy이름만 사용한다. agy --print는 stdin prompt만 사용한다. positional prompt 및 strict JSON critic 검증에 실패하면 Claude critic으로 대체한다.
모델 역할
| Model | 역할 | 강점 |
|---|---|---|
| Claude Opus (Planner) | 전략 비전 | 리스크 통합, 아키텍처 결정 |
| Codex (Architect) | 기술 설계 | API, 파일 구조, 구현 세부 |
| Claude Opus (Critic) | 리스크 분석 | 엣지케이스, 보안, 테스트 전략 |
| Antigravity (Quick/Advisory) | freeform 보조 | 빠른 초안, UX/DX 관점, 비-schema 검토 |
EXECUTION — TASK 는 사용자 입력
Step 1: 코드베이스 정찰
Agent(
subagent_type="Explore",
model="haiku",
prompt="다음 기능 관련 코드베이스 탐색: [TASK]
보고: (1) 관련 파일/디렉토리 (2) 기존 아키텍처 패턴 (3) 주요 의존성/인터페이스. bullet."
)
결과를 RECON으로 보유.
Step 2: Round 1 독립 설계 (Anti-Herding) — Bash + Agent 동시 호출
Agent (Claude Planner):
Agent(
subagent_type="oh-my-claudecode:architect",
model="opus",
run_in_background=true,
name="planner-r1",
prompt="소프트웨어 아키텍트로서 구현 계획 수립. 기능: [TASK]. 코드베이스: [RECON]. JSON: { vision, tasks: [{id, title, desc, deps, complexity}], order, risks, files, confidence, reasoning }"
)
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 · 198 lines · 68 tokens per session scan A e17db9f92a2a
tfx-plan is a skill published in the GitHub repository tellang/triflux (7 stars, last pushed yesterday), licensed MIT. It adds 68 tokens to every session and 1,926 once invoked, about $0.0003 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
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.