Dissertation-Simulator-AgenticWorkflow: Instructions file for Claude Code

AGENTS.md

Dissertation-Simulator-AgenticWorkflow AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from idoforgod/Dissertation-Simulator-AgenticWorkflow. It costs 27,416 tokens per session, scanned A, original, MIT.

A shared instruction guide for AI coding agents working on an agent-based workflow automation project. It defines the project structure, required workflow phases, verification layers, safety rules, decision records, and memory practices.

In plain words
What is it for?
Use it to guide Claude Code, Cursor, Copilot, Codex, or similar agents while they design, implement, review, and validate automated workflows.
Why use it?
It gives different coding tools the same rules, so work stays consistent across agents and sessions. It reduces the risk of incomplete workflows, conflicting changes, and unverified results.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: SessionEnd hook event, but also the file is AGENTS.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is idoforgod/Dissertation-Simulator-AgenticWorkflow's own configuration. It tells Claude Code, Codex and OpenCode how to work on Dissertation-Simulator-AgenticWorkflow itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Dissertation-Simulator-AgenticWorkflow configures →

Reuse

Borrowing it

Nothing to install: this file belongs to idoforgod/Dissertation-Simulator-AgenticWorkflow. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/idoforgod/Dissertation-Simulator-AgenticWorkflow/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/idoforgod/Dissertation-Simulator-AgenticWorkflow

Made for: Claude Code, Codex, OpenCode.

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 Dissertation-Simulator-AgenticWorkflow AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/idoforgod/dissertation-simulator-agenticworkflow/agents-md.svg)](https://agentmods.dev/instructions/idoforgod/dissertation-simulator-agenticworkflow/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/idoforgod/dissertation-simulator-agenticworkflow/agents-md"><img src="https://agentmods.dev/badge/instructions/idoforgod/dissertation-simulator-agenticworkflow/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 27,416 This file is loaded in full into every session.
When invoked 27,416 The same file — it is already loaded in full.
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 $0.27416 $0.27416
Opus 5 $0.13708 $0.13708
Sonnet 5 $0.05483 $0.05483
Haiku 4.5 $0.02742 $0.02742

Measured 3d ago against content hash 5acafa8242ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

Dissertation-Simulator-AgenticWorkflow AGENTS.md 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 3d 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.

AGENTS.md · 1,577 lines

How it starts

The opening of the file, as written. The whole thing — 1,577 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AgenticWorkflow — AI 에이전트 공통 지시서

이 파일은 모델·도구에 무관하게 이 프로젝트에서 작업하는 모든 AI 에이전트가 따라야 할 규칙이다. Claude Code, Cursor, Copilot, Codex 등 어떤 도구를 사용하든 이 문서의 규칙이 적용된다.


1. 프로젝트 정의

에이전트 기반 워크플로우 자동화 프로젝트. 복잡한 작업을 체계적 워크플로우로 설계하고, 그 워크플로우를 실제로 구현하여 동작시키는 것이 목적이다.

최종 목표 — 2단계 프로세스

단계 산출물 성격
Phase 1: 워크플로우 설계 workflow.md 중간 산출물 (설계도)
Phase 2: 워크플로우 구현 에이전트·스크립트·자동화가 실제 동작하는 시스템 최종 산출물

workflow.md를 만드는 것은 절반이다. 그 안에 기술된 내용이 실제로 동작하는 것이 최종 목표다.

존재 이유 — DNA 유전

AgenticWorkflow는 자식 agentic workflow system을 낳는 부모 유기체다. 어떤 도메인의 자식이든, 부모의 전체 게놈을 구조적으로 내장한다.

게놈 구성요소 자식에 내장되는 형태
절대 기준 3개 workflow.md Inherited DNA 섹션 — 도메인별 맥락화
SOT 패턴 state.yaml — 단일 파일 + 단일 쓰기 지점
3단계 구조 Research → Planning → Implementation 구조 제약
5계층 검증 L0 Anti-Skip → L1 Verification → L1.5 pACS → L1.7 pCCS → L2 Review
P1 봉쇄 Python 결정론적 검증 스크립트
Safety Hook 위험 명령 차단 + TDD Guard
Adversarial Review @reviewer + @fact-checker Generator-Critic 패턴
Decision Log 자동 승인 결정의 근거 기록
Context Preservation 세션 간 기억 보존 + Knowledge Archive + RLM 패턴

유전은 선택이 아니라 구조다. 자식은 부모의 DNA를 "참고"하는 것이 아니라 내장한다. 상세: soul.md §0.

12→9 매핑: soul.md §0의 12개 구성요소 중 위 9개가 inherited_dna로 자식에 구조적으로 내장된다. 나머지 3개 — 설계 원칙 P1-P4(절대 기준에 포함), Sisyphus/Error→Resolution(행동 패턴, 구조 아님), RLM 이론(이론적 기반, 구조 아님) — 는 부모 유기체의 내부 메커니즘으로서 자식에 암묵적으로 반영되되, 별도 inherited_dna 항목으로 분리하지 않는다. soul.md 자체는 메타 문서(유전의 정의서)이므로 유전 대상이 아니다.

워크플로우 기본 구조

모든 워크플로우는 3단계로 구성된다:

  1. Research — 정보 수집 및 분석
  2. Planning — 계획 수립, 구조화, 사람의 검토/승인
  3. Implementation — 실제 실행 및 산출물 생성

각 단계에는 다음을 명시한다:

  • 수행 작업 (Task)
  • 담당 에이전트
  • 데이터 전처리/후처리
  • 산출물 (Output)
  • 사람 개입 지점 (해당 시)

2. 절대 기준

이 프로젝트의 모든 설계·구현·수정 의사결정에 적용되는 최상위 규칙이다. 아래의 모든 원칙, 가이드라인, 관례보다 상위에 있다. 어떤 원칙이든 절대 기준과 충돌하면, 절대 기준이 이긴다.

절대 기준 1: 최종 결과물의 품질

속도, 토큰 비용, 작업량, 분량 제한은 완전히 무시한다. 모든 의사결정의 유일한 기준은 최종 결과물의 품질이다. 단계를 줄여서 빠르게 만드는 것보다, 단계를 늘려서라도 품질을 높이는 방향을 선택한다.

Read the full file on GitHub · 1,577 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. 3d ago First seen · 1,577 lines · 27,416 tokens per session scan A 5acafa8242ee

Subscribe to this mod's changes

Dissertation-Simulator-AgenticWorkflow AGENTS.md is an instructions file published in the GitHub repository idoforgod/Dissertation-Simulator-AgenticWorkflow (107 stars, last pushed 3mo ago), licensed MIT. It adds 27,416 tokens to every session, about $0.1371 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 instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens