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 agentmods add commands/dev-gom/claude-code-marketplace/tasksgit clone --depth 1 https://github.com/Dev-GOM/claude-code-marketplaceWhat 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 | $0.00013 | $0.03342 |
| Opus 5 | $0.00006 | $0.01671 |
| Sonnet 5 | $0.00003 | $0.00668 |
| Haiku 4.5 | $0.00001 | $0.00334 |
Grade A, and why
tasks 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 2d 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 — 351 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Break Down Plan into Tasks
User Input
$ARGUMENTS
You MUST consider the user input before proceeding (if not empty).
⚠️ 커맨드 구분: 이것은 플러그인 커맨드 (/spec-kit:tasks)입니다. 정보 수집과 사용자 논의를 담당합니다. 실제 파일 생성/업데이트는 GitHub Spec-Kit CLI 커맨드 (/speckit.tasks)가 수행합니다.
🌐 언어 지시사항: 이 명령어를 실행할 때는 사용자의 시스템 언어를 자동으로 감지하여 해당 언어로 모든 안내, 질문, 작업 분해 가이드, 출력을 제공해야 합니다. 시스템 환경 변수(LANG, LC_ALL 등)나 사용자의 이전 대화 패턴을 분석하여 언어를 판단하세요.
⚠️ AskUserQuestion Tool Usage Guidelines
CRITICAL: When using the AskUserQuestion tool throughout this command, you MUST follow these constraints:
엄격한 제약 (Strict Constraints - 반드시 준수)
Violating these will cause the tool to FAIL:
- Questions per call: 1-4 questions maximum
- Options per question: 2-4 options (minimum 2, maximum 4) - strictly enforced
- multiSelect field: Must be explicitly specified (true or false) - not optional
- "Other" option: Automatically added by system - DO NOT include it manually
권장 제약 (Recommended Constraints - UX 최적화)
These are NOT enforced, but strongly recommended for optimal UI display:
- Header field: Maximum 12 characters (exceeding may cause truncation in UI)
- Option label: 1-5 words, concise phrasing (exceeding may cause button overflow)
Additional Info
The system automatically adds an "Other" option to every question, allowing users to provide custom text input beyond the predefined options.
기술 계획을 작고 실행 가능한 작업으로 분해하여 단계별 구현 가이드를 만듭니다.
Prerequisites
계획이 먼저 존재해야 합니다:
# 현재 브랜치 확인
CURRENT_BRANCH=$(git branch --show-current)
# 계획 파일 확인
cat "specs/$CURRENT_BRANCH/plan.md"
없다면 /spec-kit:plan을 먼저 실행하세요.
Step 1: Git 변경사항 확인
작업 분해 전에 현재 작업 디렉토리의 변경사항과 브랜치 퍼블리쉬 상태를 확인합니다:
# 변경사항 확인
git status --short
# Upstream 브랜치 확인 (퍼블리쉬 여부)
git rev-parse --abbrev-ref @{upstream} 2>/dev/null
시나리오 A: 변경사항이 없는 경우
즉시 Step 2로 이동
시나리오 B: 변경사항 있음 + Upstream 브랜치 없음 (미퍼블리쉬)
브랜치가 아직 원격에 퍼블리쉬되지 않은 상태에서 변경사항이 있는 경우:
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.
- 2d ago First seen · 351 lines · 13 tokens per session scan A 476a7c281816
tasks is a command published in the GitHub repository Dev-GOM/claude-code-marketplace (97 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 13 tokens to every session and 3,342 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.