agentmods.dev

next-task

next-task is a command for coding agents from sangrokjung/claude-forge. It costs 8 tokens per session (1,014 once invoked), scanned A, original, MIT.

A command that checks a coding project and prepares the next task. It reads project notes, Git history, changed files, and task checkboxes to find progress and the next unfinished work.

In plain words
What is it for?
Use it to calculate task progress, choose the next task based on dependencies or order, find related files and tests, and estimate the task's size.
Why use it?
It removes the need to manually inspect project status and decide what should happen next.

Command

Part of the claude-forge plugin — 33 skills, 39 commands, 17 agents shipped together

not rated 825 +5 2d ago A scan 8 tokens original MIT
View the source file sangrokjung/claude-forge sangrokjung.github.io
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/sangrokjung/claude-forge/next-task
Clone the repo
git clone --depth 1 https://github.com/sangrokjung/claude-forge

Or install claude-forge, the plugin that ships this one along with the rest of its 33 skills, 39 commands, 17 agents.

Wrote 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.

agentmods badge for next-task

README.md
[![agentmods](https://agentmods.dev/badge/commands/sangrokjung/claude-forge/next-task.svg)](https://agentmods.dev/commands/sangrokjung/claude-forge/next-task)
Your own site
<a href="https://agentmods.dev/commands/sangrokjung/claude-forge/next-task"><img src="https://agentmods.dev/badge/commands/sangrokjung/claude-forge/next-task.svg" alt="Measured on agentmods" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,014 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 5.1 $0.00008 $0.01014
Opus 5 $0.00004 $0.00507
Sonnet 5 $0.00002 $0.00203
Haiku 4.5 $0.00001 $0.00101

Measured 6d ago against content hash 517dc6e19683, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

next-task 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 6d 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.

commands/next-task.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/next-task - 다음 Task 시작 준비 (v6)

0단계: 현재 상태 확인

다음 정보를 수집한다:

  1. Git 상태

    • 현재 브랜치: git branch --show-current
    • 최근 커밋 3개: git log --oneline -3
    • 스테이징/변경 파일 유무: git status --short

  2. 프로젝트 문서

    • prompt_plan.md 존재 여부 및 최종 수정 시간
    • spec.md 존재 여부
    • CLAUDE.md 존재 여부

문서가 없으면 경고를 출력한다:

[WARN] prompt_plan.md가 없습니다.
  /planner 로 실행 계획을 먼저 생성하세요.

1단계: 진행률 계산

prompt_plan.md에서 Task 체크박스를 파싱한다:

파싱 규칙:
  - [x] 또는 - [X]  → 완료
  - [ ]              → 미완료
  중첩된 체크박스(하위 항목)는 별도 집계하지 않는다.
  최상위 Task 단위만 카운트한다.

진행률 산출:

completed = [x] 개수
total     = [x] + [ ] 개수
rate      = (completed / total) * 100

2단계: 다음 Task 식별

다음 우선순위로 Task를 선택한다:

  1. 사용자 지정: 인자로 Task 번호/설명이 주어진 경우 해당 Task
  2. 의존성 해소: depends 필드의 선행 Task가 모두 완료된 미완료 Task
  3. 순서 기반: prompt_plan.md에서 첫 번째 미완료 - [ ] Task

선택된 Task에 대해 관련 파일을 탐색한다:

  • Task 설명에 언급된 파일 경로
  • 해당 모듈/디렉토리의 기존 파일 (Glob으로 탐색)
  • 관련 테스트 파일

3단계: 복잡도 분석

Task 복잡도를 분석하여 작업 규모를 추천한다.

신호 규모 기준
단순 수정, 설정 변경, 문서 업데이트 소 파일 1-2개, 변경 < 50줄 예상
일반 구현, 컴포넌트 추가, API 엔드포인트 중 파일 3-5개, 변경 50-200줄 예상
리팩토링, 복합 기능, 다중 모듈 변경 대 파일 6개 이상, 변경 200줄 이상 예상
보안 관련, 인증/결제, 데이터 마이그레이션 대+ 보안 민감 또는 되돌리기 어려운 변경

추천 근거:

  • Task 설명의 키워드 (보안, 인증, 결제 → 규모 상향)
  • 관련 파일 수 및 크기
  • depends 체인 깊이 (깊을수록 상향)

4단계: 출력

════════════════════════════════════════════════════════════════
 Next Task (진행률: [completed]/[total] = [rate]%)
════════════════════════════════════════════════════════════════

다음 작업: [Task 번호]. [Task 이름]
작업 규모: [소/중/대]
추천 근거: [한 줄 설명]

관련 파일:
  - [파일 경로 1]
  - [파일 경로 2]
  - [파일 경로 3]

선행 완료 Task:
  [x] [Task A 이름]
  [x] [Task B 이름]

시작 방법:
  이 세션에서 바로 시작
  또는 /orchestrate --type feature (Agent Teams 병렬 개발)

════════════════════════════════════════════════════════════════

모든 Task 완료 시

════════════════════════════════════════════════════════════════
 All Tasks Complete (진행률: [total]/[total] = 100%)
════════════════════════════════════════════════════════════════

모든 Task가 완료되었습니다.

다음 단계:
  /handoff-verify     최종 검증
  /sync-docs          문서 동기화
  /web-checklist      수동 테스트 체크리스트

════════════════════════════════════════════════════════════════

Read the full file on GitHub · 129 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. 6d ago First seen · 129 lines · 8 tokens per session scan A 517dc6e19683

Subscribe to this mod's changes

next-task is a command published in the GitHub repository sangrokjung/claude-forge (825 stars, last pushed 2d ago), licensed MIT. It adds 8 tokens to every session and 1,014 once invoked, about $0.0000 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.

Planningagentsai-assistantanthropicautomationclaude-codedeveloper-tools
Related

Other commands, from other repositories

CONTEXT

Slash commands for SPEC-First development workflow.

changoo89/claude-pilot · 0 tokens

review

Review plans with multi-angle analysis (mandatory + extended + autonomous).

changoo89/claude-pilot · 13 tokens

review

Perform a thorough code review of changes in this branch.

sijeeshmiziha/visionagent · 0 tokens

01_confirm

Extract plan from conversation, create file in draft/, auto-apply non-BLOCKING improvements, move to pending.

changoo89/claude-pilot · 22 tokens

05_cleanup

Safe dead code cleanup - detect and remove unused imports and dead files with auto-apply for Low/Medium risk.

changoo89/claude-pilot · 22 tokens

add-tool

Scaffold and implement a new tool for VisionAgent.

sijeeshmiziha/visionagent · 0 tokens