jdsnack-agent-os-project: Instructions file for Codex

AGENTS.md

jdsnack-agent-os-project AGENTS.md is an instructions file for Codex, OpenCode from silverThunder09/jdsnack-agent-os-project. It costs 2,248 tokens per session, scanned A, original, MIT.

A project instruction file for JDSnack, a web service that uses AI to analyze developer resumes and job descriptions.

In plain words
What is it for?
Use it when planning, implementing, testing, reviewing, or merging JDSnack features, especially when following its specifications, model assignments, automated workflow, and human-approval rules.
Why use it?
It defines which documents guide work, how Claude and Codex divide implementation and review, and how automated feature delivery is controlled.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions Codex.

This is silverThunder09/jdsnack-agent-os-project's own configuration. It tells Codex and OpenCode 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/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/silverThunder09/jdsnack-agent-os-project

Made for: 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 jdsnack-agent-os-project AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/silverthunder09/jdsnack-agent-os-project/agents-md"><img src="https://agentmods.dev/badge/instructions/silverthunder09/jdsnack-agent-os-project/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,248 This file is loaded in full into every session.
When invoked 2,248 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 $0.02248 $0.02248
Opus 5.5 $0.00899 $0.00899
Sonnet 5.5 $0.00450 $0.00450
Haiku 4.5 $0.00225 $0.00225

Measured 19d ago against content hash 713648c36c2f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

jdsnack-agent-os-project 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 19d 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 · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

JDSnack 에이전트 안내 지도

JDSnack은 개발자 이력서와 JD를 AI로 분석하는 웹 서비스입니다. ./.agent-os/standards/index.yml에는 현재 구현할 active_specs 하나만 두고, 다음 후보는 ./.agent-os/product/spec-backlog.md에 짧게 관리합니다. 과거·대체된 기획 문서는 archive에 보관합니다.

이 파일은 긴 설명서가 아니라, 작업을 시작할 때 보는 짧은 지도입니다.

코덱스와 분업 운영

코덱스는 Spec 기획·문서 계획·기능 구현·테스트와 기본 PR 리뷰를 맡고, Claude는 명시적으로 선택된 리뷰 backend 또는 사용자 승인 폴백에서만 사용합니다. 현재 리뷰 정책은 Codex 리뷰를 바로 시작합니다. 기본 리뷰어를 Claude로 바꾸더라도 Claude 실행 불가 또는 구조화 결과 누락·오류는 review-backend-fallback.md의 절차에 따라 Codex 읽기 전용 리뷰로 넘깁니다. Codex 리뷰가 실행되지 않거나 유효한 결과를 내지 못하면 needs-human으로 중단합니다.

  • 코덱스: 문서 계획(spec), 활성 spec 기준 기능 구현 + 기능 테스트 작성과 현재 기본 PR 리뷰를 담당합니다. PR 리뷰에서는 diff와 검토 기준만 받는 격리된 읽기 전용 경로를 사용합니다.
  • 클로드: 명시적으로 선택된 리뷰 backend 또는 사용자 승인 폴백을 담당합니다. backend/frontend 소스는 직접 수정하지 않습니다.
  • PR 리뷰·자동 병합: PASS 4/5 이상, 현재 base/head SHA, PR 계약, PR CI Gate, 모든 branch-required check, 미해결 변경요청 부재를 별도 approval job이 다시 확인한 뒤 Squash auto-merge를 큐에 넣습니다. 위험도 점수는 라벨에만 사용하고 자동화 정책의 추가 사람 승인 수는 0입니다. GitHub에 실제 설정된 필수 승인 규칙은 그대로 존중합니다. 세부 절차는 review-backend-fallback.md를 따릅니다.
  • clone 직후 sh scripts/install-git-hooks.sh로 core.hooksPath=.githooks와 pre-commit/pre-push 설치를 검증합니다. pre-push는 staged/working-tree/branch diff를 Codex 읽기 전용 리뷰어에게 전달하고 PASS 4점 미만이면 push를 차단합니다.
  • 리뷰는 review-routing.md의 고정 위험도 산식과 Security·Performance·Test Coverage·Architecture 라벨을 사용합니다. scripts/review-policy.json은 dryRun=false이며, 점수·현재 SHA·필수 check를 검증한 뒤 자동 Squash 병합을 허용합니다.
  • 폴백: 코덱스가 토큰이 없어 막힐 때만, 사용자가 "네가 구현해"라고 지시하면 클로드가 직접 구현·테스트합니다. 전환·복귀·가드레일은 .agent-os/operations/worker-backends.md의 폴백 규칙을 따릅니다.
  • 무인 배치: Codex 구현 PR은 이벤트 기반 리뷰-머지 루프가 리뷰·CI를 확인합니다. 마지막 Feature가 머지되면 spec-queue.json의 eligible 후보를 자동으로 Spec으로 승격하고 T1을 다시 Codex에 디스패치합니다. 리뷰 PASS 4점 이상과 필수 게이트가 모두 통과하면 위험도 구간과 무관하게 Squash auto-merge를 큐에 넣습니다. 제품 판단·충돌은 needs-human으로 멈춥니다.

Codex 모델 정책

  • 기능 구현과 테스트 코드 작성·결과 분석의 모델 배정은 backends.json과 Worker 모델 배정을 따릅니다.
  • 빌드·lint·test·E2E 명령 실행 자체: 모델을 사용하지 않습니다.
  • 기본 PR 리뷰어는 리뷰 실행 정책을 따릅니다. 현재는 Codex가 즉시 리뷰하며, Claude를 기본으로 설정한 경우 실행 불가·누락·형식 오류는 Codex로 넘깁니다. Codex 리뷰의 실행 실패나 잘못된 결과는 needs-human으로 올립니다.
  • Claude review backend unavailable 시 REQUEST_CHANGES review는 한 번만 제출하고 findings 전체를 보존합니다. 절차는 review-backend-fallback.md를 따릅니다.

Read the full file on GitHub · 85 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. 19d ago Changed · +4 tokens per session 713648c36c2f
  2. 26d ago Changed · +2 lines · +207 tokens per session 24ad20c86696
  3. 1mo ago Changed · +3 lines · +430 tokens per session 15f6ae118e8e
  4. 1mo ago Changed · +17 tokens per session d4ff50ff21cd
  5. 2mo ago First seen · 80 lines · 1,590 tokens per session scan A 0b3838b30bbf

Subscribe to this mod's changes

jdsnack-agent-os-project AGENTS.md is an instructions file published in the GitHub repository silverThunder09/jdsnack-agent-os-project (6 stars, last pushed 14d ago), licensed MIT. It adds 2,248 tokens to every session, about $0.0090 per session on Opus 5.5. 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

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 · 9,715 tokens

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 · 7,461 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, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 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 · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,750 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens