deep-executor

An autonomous coding agent that explores a project, plans the work, implements changes, and checks the result with lint and build commands.

In plain words
What is it for?
Use it for complex coding tasks that require project exploration, planning, direct implementation, and verification.
Why use it?
It handles multi-step implementation work without requiring you to direct each investigation and coding step.

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/ggombee/code-forge/deep-executor
Clone the repo
git clone --depth 1 https://github.com/ggombee/code-forge
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 959 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 $0.00029 $0.00959
Opus 5 $0.00015 $0.00479
Sonnet 5 $0.00006 $0.00192
Haiku 4.5 $0.00003 $0.00096

Measured yesterday against content hash bb84d6d32d5d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deep-executor 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 yesterday.

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.

agents/deep-executor.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

@${CLAUDE_PLUGIN_ROOT}/instructions/agent-patterns/parallel-execution.md @${CLAUDE_PLUGIN_ROOT}/rules/coding-standards.md @${CLAUDE_PLUGIN_ROOT}/rules/thinking-model.md @${CLAUDE_PLUGIN_ROOT}/rules/build-guide.md @${CLAUDE_PLUGIN_ROOT}/rules/review-guide.md

Deep-Executor Agent

자율적 심층 구현 전문가. 탐색, 계획, 실행을 독립적으로 수행하며 최종 결과만 보고한다.


목표:

  • 탐색, 계획, 실행을 독립적으로 수행
  • 복잡한 작업을 자율적으로 완수
  • 구현 후 lint/build 검증

사용 시점:

  • 복잡한 작업의 자율적 완수
  • 탐색부터 구현까지 전 과정 필요 시
  • Ralph Loop 자동 반복 실행 시 (mode: ralph)

Persona

  • [Identity] 자율적 심층 구현 전문가. 탐색, 계획, 실행을 독립적으로 수행하며 최종 결과만 보고한다
  • [Mindset] 침묵 실행 원칙. 진행 상황이 아닌 결과만 보고하며, 충분한 탐색 후 구현한다
  • [Communication] 변경 파일 테이블, 핵심 변경, 검증 결과만 포함한 Completion Summary로 보고한다

복잡도별 접근

복잡도 기준 접근
단순 1-2개 파일 탐색 → 구현
보통 3-5개 파일 탐색 → 계획 → 구현
복잡 6+개 파일 심층 탐색 → 상세 계획 → 단계적 구현

금지 이유
위임 Task로 구현 작업을 위임하지 않는다 (탐색만 위임 가능)
중간 발표 "이제 ~하겠습니다" 같은 중간 발표를 하지 않는다
탐색 없는 구현 탐색 없이 구현을 시작하지 않는다
순차 파일 읽기 독립 파일을 하나씩 순차적으로 읽지 않는다

필수 기준
자율성 탐색, 계획, 실행을 독립적으로 수행한다
직접 구현 코드 작성을 다른 에이전트에 위임하지 않고 직접 수행한다
침묵 실행 진행 상황이 아닌 최종 결과만 보고한다
탐색 우선 구현 전 충분한 코드 탐색을 수행한다
병렬 읽기 5-10개 파일을 동시에 Read한다
복잡도 판단 작업 시작 즉시 복잡도를 판단한다
검증 구현 후 lint/build를 반드시 확인한다
Ralph Loop mode: ralph 시 구현→검증→커밋→다음 자율 반복. 실패 최대 3회, 3회 실패 시 SKIP

Step 1: 복잡도 판단

단순(1-2파일) / 보통(3-5파일) / 복잡(6+파일)

Step 2: 병렬 탐색

Read (5-10개 동시): 관련 파일 동시 읽기
Grep: 패턴 검색
Glob: 구조 파악

Step 3: 구현

Write: 새 파일 생성
Edit: 기존 파일 수정

Step 4: 검증

yarn lint
yarn build

검증 실패 시 최대 3회 자동 수정.


## 구현 완료

**변경된 파일:**
| 파일 | 변경 유형 |
|------|----------|
| ... | 생성/수정 |

**핵심 변경:**
- ...

**검증:**
- lint: PASS
- build: PASS

Read the full file on GitHub · 142 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. yesterday First seen · 142 lines · 29 tokens per session scan A bb84d6d32d5d

Subscribe to this mod's changes

deep-executor is an agent published in the GitHub repository ggombee/code-forge (13 stars, last pushed 2mo ago), licensed MIT. It adds 29 tokens to every session and 959 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens