task-analyzer

task-analyzer is a skill for Claude Code from Kit4Some/Oh-my-ClaudeClaw. It costs 114 tokens per session (1,665 once invoked), scanned A, original, MIT.

A planning and execution skill that turns a request into smaller tasks and an ordered work plan. It can identify needed tools, delegate parts to other agents, collect results, and save relevant context for later.

In plain words
What is it for?
Use it for research, reports, multi-step file work, and other tasks that need planning, tool selection, delegation, and a final summary.
Why use it?
It helps with requests that are too large or unclear to handle as one step. It also makes the intended result and completion conditions explicit before work begins.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: built for openclaw.

Part of the openclaw-cc plugin — 22 skills, 4 agents, 5 MCP servers shipped together

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 skills/kit4some/oh-my-claudeclaw/task-analyzer
Any agent
npx skills add Kit4Some/Oh-my-ClaudeClaw --skill task-analyzer
Clone the repo
git clone --depth 1 https://github.com/Kit4Some/Oh-my-ClaudeClaw

Made for: Claude Code.

Or install openclaw-cc, the plugin that ships this one along with the rest of its 22 skills, 4 agents, 5 MCP servers.

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 task-analyzer

README.md
[![agentmods](https://agentmods.dev/badge/skills/kit4some/oh-my-claudeclaw/task-analyzer.svg)](https://agentmods.dev/skills/kit4some/oh-my-claudeclaw/task-analyzer)
Your own site
<a href="https://agentmods.dev/skills/kit4some/oh-my-claudeclaw/task-analyzer"><img src="https://agentmods.dev/badge/skills/kit4some/oh-my-claudeclaw/task-analyzer.svg" alt="Measured on agentmods" height="20"></a>
Per session 114 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,665 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 $0.00114 $0.01665
Opus 5 $0.00057 $0.00833
Sonnet 5 $0.00023 $0.00333
Haiku 4.5 $0.00011 $0.00167

Measured 6d ago against content hash 39f62fe2c105, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

task-analyzer 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.

.claude/skills/task-analyzer/SKILL.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task Analyzer — 자율 작업 분석 & 실행 엔진

역할

사용자의 요청을 분석하여 실행 가능한 계획으로 변환하고, 가용한 도구(MCP 서버, 서브에이전트, 파일 시스템)를 활용하여 자율적으로 실행한다. 작업 시작 전 memory_search로 관련 컨텍스트를 확인하고, 완료 후 memory_store로 결과를 저장한다.

5-Phase 프로세스

Phase 1 — 요청 이해

사용자 요청을 4가지 축으로 분석한다:

질문 예시
What (의도) 무엇을 달성하려는가? "경쟁사 현황 파악"
Done when (성공 기준) 어떤 상태가 되면 완료인가? "비교 테이블이 포함된 보고서 완성"
With what (리소스) 어떤 도구/데이터가 필요한가? "웹 검색, 메모리의 기존 경쟁사 데이터"
Constraints (제약) 시간/범위/형식 제한이 있는가? "한국어, 3페이지 이내"

불명확한 요청은 사용자에게 확인 질문을 한다. 명확한 요청은 즉시 Phase 2로.

Phase 2 — 작업 분해

복잡한 작업을 원자적 서브태스크 트리로 분해한다.

[작업] 경쟁사 분석 보고서 작성
├── [컨텍스트] memory_search("경쟁사") → 기존 데이터 확인
├── [수집] 경쟁사 A 최신 동향 조사 → web_search
├── [수집] 경쟁사 B 최신 동향 조사 → web_search (∥ 병렬 가능)
├── [분석] 강점/약점 비교 매트릭스 → reasoning
├── [생성] 보고서 초안 작성 → file creation
├── [저장] memory_store(category:"projects", tags:["경쟁사","분석"])
└── [알림] messenger_send(platform:"telegram", message:"보고서 완성")

분해 패턴 12가지는 references/decomposition-patterns.md 참조.

Phase 3 — 실행 전략 선택

전략 조건 예시
순차 서브태스크 간 선후 의존성 존재 조사 → 분석 → 작성
병렬 독립적인 서브태스크 (서브에이전트 위임) 경쟁사 A 조사 ∥ B 조사 ∥ C 조사
하이브리드 병렬 수집 → 순차 분석 → 병렬 출력 대부분의 복합 작업

서브에이전트 위임 기준: 독립적이고, 3단계 이상이며, 결과가 다른 태스크에 즉시 필요하지 않은 작업.

Phase 4 — 실행 & 모니터링

각 서브태스크 실행 후 상태를 판정한다:

  • 성공 → 결과를 수집하고 다음 태스크로 진행
  • 부분 성공 → 획득한 결과를 저장, 누락 부분을 기록하고 진행
  • 실패 → 대안 전략 시도 (최대 2회). 대안도 실패 시 사용자에게 보고

실행 중 발견된 중요 정보는 즉시 memory_daily_log로 기록한다.

Phase 5 — 결과 수집 & 보고

  1. 모든 서브태스크 결과를 통합
  2. 핵심 결과물을 memory_store로 영구 저장
  3. 실행 로그를 memory_daily_log(type:"done")로 기록
  4. 필요 시 messenger_send로 사용자 알림
  5. 아래 출력 포맷으로 최종 보고

가용 도구 매핑 테이블

작업 유형 MCP 도구 비고
과거 컨텍스트 조회 memory_search, memory_get 작업 시작 시 항상 먼저 호출
정보 영구 저장 memory_store, memory_update 결과물·인사이트 저장
실행 로그 기록 memory_daily_log type: note/decision/todo/done
메모리 현황 확인 memory_stats, memory_list 저장소 상태 파악
메모리 삭제 memory_delete 중복·불필요 데이터 정리
웹 조사 web_search, web_fetch 외부 정보 수집
외부 알림 messenger_send platform: discord/telegram/all
메신저 확인 messenger_read, messenger_poll 사용자 메시지 확인
메신저 상태 messenger_status 플랫폼 연결 상태
예약 작업 등록 task_create, task_update cron 표현식 포함
예약 작업 조회 task_list, task_history 기존 태스크 확인
예약 작업 실행 task_run_now, task_delete 즉시 실행 또는 삭제
crontab 생성 task_generate_crontab 시스템 crontab 파일 출력
파일 생성/편집 내장 파일 도구 보고서, 문서 작성
코드/명령 실행 bash 서브에이전트로 위임 권장

Read the full file on GitHub · 138 lines

Files

What ships with it

3 files 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.

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 · 138 lines · 114 tokens per session scan A 39f62fe2c105

Subscribe to this mod's changes

task-analyzer is a skill published in the GitHub repository Kit4Some/Oh-my-ClaudeClaw (4 stars, last pushed 5mo ago), licensed MIT. It adds 114 tokens to every session and 1,665 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

ready

From any input — a natural-language goal, existing docs (spec / plan / brain-dump), notes, or a mix — interactively elicit and validate intent and produce an execution-ready 3-doc (handoff, spec, plan) for go, replacing third-party brainstorming + planning in one skill. Input format is open; the input is material, not…

fn-opt/dryforge · 92 tokens

messaging

Set up a messaging channel (WhatsApp, Telegram, Discord, iMessage, Slack) to reach this agent from outside Claude Code. Triggers on /agent:messaging, "configurar whatsapp", "setup messaging", "conectar telegram", "agregar canal".

crisandrews/ClawCode · 58 tokens

voice

Voice — text-to-speech and transcription. Triggers on /agent:voice, /agent:voice status, /agent:voice setup, /agent:voice test, "configurar voz", "prueba voz", "voice setup", "speak this", "read this aloud", "transcribe audio".

crisandrews/ClawCode · 66 tokens

new

Start a new session — save summary to memory, then mark as reset so next message gets a fresh greeting. OpenClaw-compatible. Triggers on /new, /reset, /agent:new, "nueva sesión", "new session", "reset".

crisandrews/ClawCode · 54 tokens

status

Show agent runtime status — identity, model, context, memory, crons, voice. Works from CLI or messaging. Triggers on /status, /agent:status, "status del agente", "cómo estás técnicamente".

crisandrews/ClawCode · 48 tokens

compact

Flush important session context to daily log (manual memory flush). Does NOT invoke native /compact. Triggers on /compact, /agent:compact, /flush, "guarda memoria", "flush".

crisandrews/ClawCode · 43 tokens