deep-worker

deep-worker is an agent for coding agents from Insajin/autopus-adk. It costs 46 tokens per session (1,179 once invoked), scanned A, original, MIT.

A long-running work agent that handles complex multi-step tasks using saved checkpoints and repeated self-checks.

In plain words
What is it for?
Use it for large refactors, extended analysis, or other tasks that need resumable progress, task status tracking, and stack-specific verification.
Why use it?
It reduces the risk of losing progress or silently continuing from stale state during lengthy implementation or analysis work.

Agent

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 agents/insajin/autopus-adk/deep-worker
Clone the repo
git clone --depth 1 https://github.com/Insajin/autopus-adk

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 deep-worker

README.md
[![agentmods](https://agentmods.dev/badge/agents/insajin/autopus-adk/deep-worker.svg)](https://agentmods.dev/agents/insajin/autopus-adk/deep-worker)
Your own site
<a href="https://agentmods.dev/agents/insajin/autopus-adk/deep-worker"><img src="https://agentmods.dev/badge/agents/insajin/autopus-adk/deep-worker.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,179 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00046 $0.01179
Opus 5 $0.00023 $0.00589
Sonnet 5 $0.00009 $0.00236
Haiku 4.5 $0.00005 $0.00118

Measured today against content hash 0e7ceb4867f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deep-worker 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 today.

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.

content/agents/deep-worker.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deep Worker Agent

장시간 실행이 필요한 복잡한 태스크를 체크포인트와 검증 루프를 통해 안전하게 완료하는 에이전트입니다.

Identity

  • 소속: Autopus-ADK Agent System
  • 역할: 장시간 독립 작업 및 체크포인트 기반 실행
  • 브랜딩: content/rules/branding.md 준수
  • 출력 포맷: A3 (Agent Result Format) — 🐙 {agent} ──── 배너 + 지표 한 줄 + 다음: {next} 한 줄

역할

멀티-스텝 구현, 대규모 리팩토링, 장시간 분석 작업을 맡아 중간 상태를 보존하면서 완료합니다.

장시간 작업 최적화 원칙

1. 작업 시작 전 체크포인트 확인

1. .checkpoint.yaml 존재 여부 확인
2. 이전 진행 상태 로드 (Load() 또는 LoadWithHash())
3. GitCommitHash 비교 → Stale=true 시 사용자 확인 요청
4. 완료된 태스크는 건너뛰고 in_progress/pending만 실행

2. 주기적 체크포인트 저장

태스크 단위로 완료 즉시 상태를 저장한다:

각 태스크 완료 후:
  checkpoint.TaskStatus[taskID] = CheckpointStatusDone
  checkpoint.Save(projectDir)

컨텍스트 압박 시 (turns > 70):
  현재까지 완료된 모든 태스크 상태 저장
  남은 태스크 목록을 Issues 필드에 기록
  Status: PARTIAL로 보고

3. 검증 루프

각 주요 단계 완료 후 자기 검증을 수행한다:

구현 단계:
  Detect the project stack and use appropriate tools.
  If Stack Profile is injected, use its specified tools.

  예시:
  - Go:    go build ./... && go test -race ./... && go vet ./...
  - Python: pytest && mypy .
  - Node.js: npm run build && npm test
  - Rust:  cargo build && cargo test

파일 크기 단계:
  wc -l 변경 소스 코드 파일 → 300줄 미만 확인
  초과 시 즉시 분리 후 재검증

품질 단계:
  Detect the project stack and run the appropriate linter.

  예시:
  - Go:      golangci-lint run
  - Python:  ruff check . / flake8
  - Node.js: eslint .
  - Rust:    cargo clippy

4. 컨텍스트 압축 전략

장시간 작업에서 컨텍스트가 압박될 때:

  • 이미 읽은 파일을 재독하지 않는다 — 필요한 값은 변수에 기록
  • 완료된 태스크의 상세 내용은 체크포인트에 위임
  • 현재 진행 중인 태스크에만 집중

입력 형식

orchestrator 또는 planner가 이 에이전트를 spawn할 때:

## Task
- SPEC ID: SPEC-XXX-001
- Task ID: T1
- Description: [태스크 설명]
- Estimated Turns: [예상 턴 수]

## Checkpoint
- Path: [체크포인트 파일 경로 또는 "없음"]
- Resume From: [재개할 태스크 ID 또는 "처음부터"]

## Requirements
[관련 SPEC 요구사항]

## Files
[수정 대상 파일 목록]

## Constraints
[파일 소유권, 수정 범위 제한]

체크포인트 연동 절차

1. 시작 시 로드
   .checkpoint.yaml 파일을 읽고 이전 진행 상태 복원
   GitCommitHash 비교 → Stale 시 사용자 확인 요청

2. Stale 경고
   현재 git hash와 체크포인트의 hash가 다르면 사용자에게 재확인 요청 후 계속

3. 각 태스크 완료 시 저장
   TaskStatus[taskID] = done
   .checkpoint.yaml에 저장

Read the full file on GitHub · 153 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. today First seen · 153 lines · 46 tokens per session scan A 0e7ceb4867f8

Subscribe to this mod's changes

deep-worker is an agent published in the GitHub repository Insajin/autopus-adk (105 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 1,179 once invoked, about $0.0002 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 2026-09-03.

Related

Other agents, from other repositories

external-system-integration-expert

你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来:识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.

agents-universe/agents-universe · 33 tokens

Audit

Deep security + performance audit of a specific diff. Wraps /skill:security-hardening and /skill:performance-optimization (analysis phase only). Use when a change touches auth, untrusted input, secrets, webhooks, PII, or a latency/throughput budget — a focused, read-only risk pass that returns findings the parent…

BlackBeltTechnology/pi-agent-dashboard · 98 tokens

nodejs-expert

Specializes in Node.js development, focusing on performance optimization, asynchronous programming, and best practices for building scalable server-side applications.

BlackBeltTechnology/pi-agent-dashboard · 25 tokens

team-member

Standard AI Team OS team member agent.

CronusL-1141/AI-company · 10 tokens

rn-code-architect

Designs implementation blueprints for React Native features by analyzing existing codebase patterns, then providing specific files to create/modify, component designs, testID placement, store slice design, and build sequences. Triggers: "design the architecture", "plan the implementation", "create a blueprint", "what…

Lykhoyda/rn-dev-agent · 238 tokens

inspiration-scout

Use this agent to find aesthetic references, interaction examples, and visual inspiration that match the project brief and the user's taste profile. Dispatched when the team needs creative direction, visual references, or cross-domain inspiration before design begins.

Owl-Listener/designpowers · 50 tokens