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-indexgit 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-index)<a href="https://agentmods.dev/skills/tellang/triflux/tfx-index"><img src="https://agentmods.dev/badge/skills/tellang/triflux/tfx-index/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-index"><img src="https://agentmods.dev/badge/skills/tellang/triflux/tfx-index.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00080 | $0.01396 |
| Opus 5 | $0.00040 | $0.00698 |
| Sonnet 5 | $0.00016 | $0.00279 |
| Haiku 4.5 | $0.00008 | $0.00140 |
Grade A, and why
tfx-index 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 12d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tfx-index — Project Indexing (94% Token Reduction)
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.
SuperClaude index-repo 오마주. 1회 2K 토큰으로 인덱스 생성, 이후 세션마다 55K 토큰 절감.
Antigravity 위임: 스캔 + 인덱스 생성 작업은 Antigravity CLI에 위임한다. Claude는 모드 선택(Step 0)과 파일 쓰기만 담당. Claude 토큰 소비 ~500 tokens으로 줄어든다.
원리
매 세션마다 프로젝트 구조를 파악하려면 수십 개 파일을 읽어야 한다 (~58K tokens). 인덱스를 한 번 생성하면 3K 토큰짜리 PROJECT_INDEX.md만 읽으면 된다.
ROI: 1회 투자 2K → 세션당 55K 절감 → 10세션이면 550K 절감
워크플로우
Step 0: 인덱싱 모드 선택
인자 없이 호출되거나 모드가 불명확한 경우, AskUserQuestion으로 모드를 선택받는다:
AskUserQuestion:
"인덱싱 모드를 선택하세요:"
1. 전체 인덱스 생성 (처음 또는 재생성)
2. 증분 업데이트 (변경분만)
3. 특정 디렉토리만
- 1번 선택 → Step 1부터 전체 실행
- 2번 선택 →
--update모드로 전환 (기존 인덱스 필요, 없으면 1번으로 fallback) - 3번 선택 → 추가 AskUserQuestion으로 대상 디렉토리 경로 입력받음
--update 플래그나 경로 인자가 이미 제공된 경우 이 단계를 건너뛴다.
Step 1: Antigravity에 스캔 + 인덱스 생성 위임
Claude는 프로젝트 경로와 모드를 Antigravity에 전달하고, Antigravity가 파일 트리 스캔·메타데이터 추출·인덱스 생성을 모두 수행한다.
Bash("TFX_CLI_MODE=antigravity bash ~/.claude/scripts/tfx-route.sh antigravity 'Scan the project at {path}. For each source file, extract: exports, imports, line count, file type. Exclude node_modules/, .git/, dist/, build/, coverage/, *.lock, *.log, *.map. Generate both PROJECT_INDEX.md and PROJECT_INDEX.json following this format:
PROJECT_INDEX.md:
# PROJECT_INDEX.md
Generated: {date} | Files: {count} | Lines: {total_lines}
## Architecture
{1-2 line summary}
## Directory Map
{tree with inline comments}
## Key Files
| File | Lines | Exports | Role |
## Dependencies
| Package | Version | Purpose |
## Entry Points
- {entry}: {role}
PROJECT_INDEX.json:
{
"generated": "{date}",
"stats": { "files": N, "lines": N },
"files": { "{path}": { "lines": N, "exports": [], "imports": [], "type": "" } },
"graph": { "{path}": ["{dep}", ...] }
}
Return the full content of both files separated by the delimiter: ===PROJECT_INDEX_JSON_START===
Mode: {mode}
'")
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.
- 12d ago First seen · 147 lines · 80 tokens per session scan A a8e6634d70a2
tfx-index is a skill published in the GitHub repository tellang/triflux (7 stars, last pushed 3d ago), licensed MIT. It adds 80 tokens to every session and 1,396 once invoked, about $0.0004 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
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.
lucia-relay
Transfer unfinished work and non-obvious knowledge across sessions, agents, people, machines, or harnesses. Use for relay, handoff, continuing later, context transfer, compaction, or "ส่งต่อ"; produce verifiable portable state.
handover
Use when wrapping up or capturing the current state of a coding session — writes a short, dated entry to the repo's RepoHandover.md so a future agent or you can resume without grepping archived sessions. Triggers on "handover", "hand off", "write handover", "capture state", "checkpoint this session".
neo4j-agent-memory-skill
Authoritative reference for the neo4j-agent-memory Python package — a graph-native memory system for AI agents built on Neo4j — and for the hosted service (NAMS) at memory.neo4jlabs.com. Use this skill whenever the user mentions neo4j-agent-memory, agent memory with Neo4j, context graphs, the POLE+O model…
boss-briefing
Vault health check — workflow pattern analysis, profile sync, session gap recovery, persona rule proposals.
briefing-vault
Initialize, manage, and search the per-project .briefing/ vault. Obsidian-compatible persistent knowledge base.