ml

ml is a command for Claude Code from dancinlab/hexa-lang. It costs 0 tokens per session (865 once invoked), scanned A, original, MIT.

A command for managing a machine-learning development roadmap, showing unfinished and proposed work in formatted tables. Machine learning is software that learns patterns from data.

In plain words
What is it for?
Use it to list roadmap items, start or plan the next task, mark work complete, add items, and synchronize roadmap files.
Why use it?
It keeps completed items out of the active list and makes unfinished work, priorities, counts, and GPU-dependent tasks visible.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/dancinlab/hexa-lang/ml
Clone the repo
git clone --depth 1 https://github.com/dancinlab/hexa-lang

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 865 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00865
Opus 5 $0.00000 $0.00432
Sonnet 5 $0.00000 $0.00173
Haiku 4.5 $0.00000 $0.00086

Measured 3d ago against content hash e0f42191ebdd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ml 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 3d 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.

.claude/commands/ml.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ML 다음 레벨 로드맵을 관리한다.

⛔ 표시 규칙 (절대 위반 금지)

  1. status="done" 항목은 절대 표시하지 않는다 — todo와 partial만 표시
  2. 매 행 사이에 ├────┼── 가로 구분선을 반드시 넣는다
  3. 표시할 항목이 20개 미만이면 새 항목을 제안하여 20개까지 같은 표 안에 채운다ml add 텍스트가 아니라 동일한 box-drawing 표 형식으로 행 추가. 상태 컬럼에 "제안" 표시
  4. 하단에 done/partial/todo 카운트 표시
  5. H100/GPU 필요 항목은 별도 표로 맨 마지막에 H100 컬럼 포함하여 표시

실행 절차

  1. shared/hexa-lang/ml-next-level.json 을 읽는다 (SSOT).
  2. 인자($ARGUMENTS)에 따라 분기:

인자 없음 또는 "list"

  • JSON에서 status가 "todo" 또는 "partial"인 항목만 필터링
  • 아래 형식으로 출력 (done 항목은 절대 포함하지 않는다):
┌────┬──────────────────────┬─────────────────────────────┬──────────────────┬────────┐
│ #  │ 영역                 │ 설명                        │ 영향             │ 상태   │
├────┼──────────────────────┼─────────────────────────────┼──────────────────┼────────┤
│ 51 │ Pipeline Parallelism │ 레이어 분할 마이크로배치     │ 대규모 학습 효율 │ 제안   │
├────┼──────────────────────┼─────────────────────────────┼──────────────────┼────────┤
│ 52 │ ZeRO Optimizer       │ 옵티마이저 상태 분할         │ 메모리 8x 절감   │ 제안   │
├────┼──────────────────────┼─────────────────────────────┼──────────────────┼────────┤
│ .. │ ...                  │ ...                         │ ...              │ 제안   │
└────┴──────────────────────┴─────────────────────────────┴──────────────────┴────────┘

⚠️ H100/GPU 필요 (confirm 후 진행):
┌────┬──────────────────────┬─────────────────────────────┬──────────────────┬────────┬──────┐
│ #  │ 영역                 │ 설명                        │ 영향             │ 상태   │ H100 │
├────┼──────────────────────┼─────────────────────────────┼──────────────────┼────────┼──────┤
│ 20 │ Tensor Parallelism   │ GPU 간 분할                  │ 단일 GPU 초과    │ todo   │ 필수 │
└────┴──────────────────────┴─────────────────────────────┴──────────────────┴────────┴──────┘
done: 49 / todo: 1 / 제안: 19  (총 50개)

"go" (메인 명령어)

  • status=todo|partial 전부 병렬 bg Agent 발사 (run_in_background: true 필수)
  • 확인 질문 없이 즉시 실행
  • 포그라운드 Agent 금지

"next"

  • 최우선 항목 계획 → 확인 → 구현

숫자 (예: "5")

  • 해당 id 항목 구현 시작

Read the full file on GitHub · 64 lines

Changes

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.

  1. 3d ago First seen · 64 lines · 0 tokens per session scan A e0f42191ebdd

Subscribe to this mod's changes

ml is a command published in the GitHub repository dancinlab/hexa-lang (196 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 865 tokens. 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 2026-08-30.