jdsnack-agent-os-project: Instructions file for Claude Code

CLAUDE.md

jdsnack-agent-os-project CLAUDE.md is an instructions file for Claude Code from silverThunder09/jdsnack-agent-os-project. It costs 1,006 tokens per session, scanned A, original, MIT.

Repository instructions for a project that uses Claude and Codex as separate development roles. They assign planning, review, and integration work to Claude, while Codex handles implementation and functional tests.

In plain words
What is it for?
Use them when contributing to the JDSnack project, an application that matches résumés with job descriptions. They guide planning, implementation, reviews, builds, tests, and pull-request handling.
Why use it?
They make responsibilities clear and reduce duplicated work between the two coding agents. They also describe which checks and delivery steps belong to each role.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions AGENTS.md; mentions Codex.

This is silverThunder09/jdsnack-agent-os-project's own configuration. It tells Claude Code how to work on jdsnack-agent-os-project 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 jdsnack-agent-os-project configures →

Reuse

Borrowing it

Nothing to install: this file belongs to silverThunder09/jdsnack-agent-os-project. 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/silverThunder09/jdsnack-agent-os-project/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/silverThunder09/jdsnack-agent-os-project

Made for: Claude Code.

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 jdsnack-agent-os-project CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/silverthunder09/jdsnack-agent-os-project/claude-md/github.svg)](https://agentmods.dev/instructions/silverthunder09/jdsnack-agent-os-project/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/silverthunder09/jdsnack-agent-os-project/claude-md"><img src="https://agentmods.dev/badge/instructions/silverthunder09/jdsnack-agent-os-project/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for jdsnack-agent-os-project CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/silverthunder09/jdsnack-agent-os-project/claude-md"><img src="https://agentmods.dev/badge/instructions/silverthunder09/jdsnack-agent-os-project/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,006 This file is loaded in full into every session.
When invoked 1,006 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.01006 $0.01006
Opus 5 $0.00503 $0.00503
Sonnet 5 $0.00201 $0.00201
Haiku 4.5 $0.00101 $0.00101

Measured 9d ago against content hash 1aa16e0ce9e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

jdsnack-agent-os-project CLAUDE.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 9d 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.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

JDSnack(이력서↔JD AI 매칭) 작업 규칙·계약·탐색정책·Git 규약의 정본은 AGENTS.md.agent-os/ 입니다. 작업 전 AGENTS.md를 먼저 읽으세요. 이 파일은 Claude 전용 역할 경계와 명령어만 보강합니다.

Claude의 역할 (Codex와 분업)

Claude는 기획·검증·리뷰·통합을 맡고, 기능 구현·테스트는 하지 않습니다. 구현과 기능 테스트는 Codex가 담당합니다.

  • ✅ 문서 계획·작성 → doc-planner 서브에이전트 또는 메인 plan 모드. 모델 배정은 backends.json을 따른다. .agent-os/ 하네스 규칙(doc-lifecycle.md·definition-of-done.md 등)에 맞춘다.
  • ✅ 게이트 검증 → 빌드/lint/test/e2e(아래 명령)로 Codex 산출물을 확인한다.
  • ✅ 독립 리뷰·채점 → code-reviewer 서브에이전트에 diff와 합격기준만 넘겨 5점 채점(/review-loop). 레포 전체를 주입하지 않는다.
  • ✅ PR 생성·관리 → 이벤트 기반 자동 루프. 일반 codex/* 구현 PR과 자동 생성된 Spec promotion PR은 게이트 통과 시 자동 머지하고, High-risk·충돌·사람 판단이 필요한 큐 후보는 needs-human으로 중단합니다.
  • 기능 구현 + 기능 테스트 작성, 리뷰 기반 코드 수정·커밋·푸시 → Codex 담당.
  • ❌ CI/CD 배포(GHCR publish, compose.prod.yaml, 배포 워크플로/런북, 자동 배포·검증) → Codex 담당(사용자 지시 시).

Claude는 backend/src, frontend/src 등 소스 코드를 직접 수정하지 않습니다. 리뷰에서 문제를 찾으면 직접 고치지 말고 code-reviewer 형식의 변경요청으로 정리해 Codex에 넘깁니다. 단, 이미 리뷰를 통과한 변경을 PR로 마무리하는 커밋·푸시는 Claude가 할 수 있습니다(PR 관리 범위).

폴백: Codex 토큰 부재 시 Claude 직접 구현

전환·복귀·가드레일의 정본은 .agent-os/operations/worker-backends.md의 폴백 규칙이다. 요지: Codex 인증·쿼터 장애 판정 시 사용자 승인(outage당 1회, 기존 "네가 구현해" 지시) 후 Claude가 활성 spec(requirements·acceptance-criteria·test-scenarios·api-spec·ui-spec)을 읽고 그대로 구현·테스트한다. 이 동안 만든 PR은 자동 머지에서 제외되고 사용자 머지로 강등된다(자기 구현·자기 검수 차단). Codex 가용성이 확인되면 다음 티켓부터 자동 복귀한다.

컨텍스트 관리: 무거운 작업은 서브에이전트로

Claude의 기획·리뷰·탐색 중 토큰 무거운 bounded 작업은 서브에이전트에 위임해 메인 세션을 린(lean)하게 유지한다: spec 작성=doc-planner, 코드베이스 탐색=Explore/general-purpose(결론만), 독립 리뷰=code-reviewer(diff만). 기능이 바뀌면 새 세션을 시작한다(상태는 메모리가 이어줌).

빌드 / 테스트 (게이트·검증용)

cd backend && ./gradlew test            # 백엔드 테스트
cd frontend && npm run lint && npm test # 프론트 lint + 테스트
cd frontend && npm run test:e2e         # playwright
docker compose up --build               # 전체 기동 backend:8080 / frontend:5173

잊지 말 것

  • 규칙·계약·탐색정책·Git 규약은 모두 AGENTS.md.agent-os/ 참조 (여기서 재서술하지 않음)
  • 비밀 키는 서버에서만 처리(프론트 입력·저장 금지)
  • 역할별 모델 배정은 backends.jsonWorker 모델 배정을 따른다.

Read the full file on GitHub · 41 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. 9d ago First seen · 41 lines · 1,006 tokens per session scan A 1aa16e0ce9e4

Subscribe to this mod's changes

jdsnack-agent-os-project CLAUDE.md is an instructions file published in the GitHub repository silverThunder09/jdsnack-agent-os-project (5 stars, last pushed today), licensed MIT. It adds 1,006 tokens to every session, about $0.0050 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 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 · 5,153 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

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens