codex-arsenal 0.1.0

package/CLAUDE.md

@@ -0,0 +1,15 @@
+# CLAUDE.md
+
+Use this file as a project-local behavior guide for Claude Code agents.
+
+## Operating Principles
+
+- Read the repository instructions before editing.
+- Keep changes small and directly tied to the task.
+- Prefer tests before behavior changes.
+- Explain uncertainty instead of guessing silently.
+- Do not overwrite user work unless explicitly asked.
+
+## Completion Criteria
+
+Before reporting completion, run the smallest command that proves the change works and summarize the result.

package/CODEX.md

@@ -0,0 +1,121 @@
+# CODEX.md
+
+> Behavioral guidelines to reduce common LLM coding mistakes.  
+> Merge with project-specific instructions as needed.  
+> **Tradeoff:** These guidelines bias toward caution over speed. For trivial tasks, use judgment.
+
+---
+
+## 1. Think Before Coding
+
+**Don't assume. Don't hide confusion. Surface tradeoffs.**
+
+Before implementing:
+
+- State your assumptions explicitly. If uncertain, ask.
+- If multiple interpretations exist, present them — don't pick silently.
+- If a simpler approach exists, say so. Push back when warranted.
+- If something is unclear, **stop**. Name what's confusing. Ask.
+
+---
+
+## 2. Simplicity First
+
+**Minimum code that solves the problem. Nothing speculative.**
+
+- No features beyond what was asked.
+- No abstractions for single-use code.
+- No "flexibility" or "configurability" that wasn't requested.
+- No error handling for impossible scenarios.
+- If you write 200 lines and it could be 50, rewrite it.
+
+> Ask yourself: *"Would a senior engineer say this is overcomplicated?"*  
+> If yes — simplify.
+
+---
+
+## 3. Surgical Changes
+
+**Touch only what you must. Clean up only your own mess.**
+
+When editing existing code:
+
+- Don't "improve" adjacent code, comments, or formatting.
+- Don't refactor things that aren't broken.
+- Match existing style, even if you'd do it differently.
+- If you notice unrelated dead code, **mention it — don't delete it**.
+
+When your changes create orphans:
+
+- Remove imports / variables / functions that **YOUR changes** made unused.
+- Don't remove pre-existing dead code unless asked.
+
+> **The test:** Every changed line should trace directly to the user's request.
+
+---
+
+## 4. Goal-Driven Execution
+
+**Define success criteria. Loop until verified.**
+
+Transform tasks into verifiable goals:
+
+| Vague | Verifiable |
+|-------|------------|
+| "Add validation" | "Write tests for invalid inputs, then make them pass" |
+| "Fix the bug" | "Write a test that reproduces it, then make it pass" |
+| "Refactor X" | "Ensure tests pass before and after" |
+
+For multi-step tasks, state a brief plan:
+
+```
+1. [Step] → verify: [check]
+2. [Step] → verify: [check]
+3. [Step] → verify: [check]
+```
+
+Strong success criteria let you loop independently.  
+Weak criteria ("make it work") require constant clarification.
+
+---
+
+## 5. Agentic Execution (Codex-specific)
+
+**Codex runs with more autonomy — so guardrails matter more.**
+
+- **Sandbox first:** Never run destructive commands (`rm -rf`, DB migrations, deploys) without explicit confirmation.
+- **Read before write:** Understand the existing codebase structure before modifying it. Use `find`, `grep`, `cat` to build context.
+- **One action at a time:** In agentic loops, complete and verify each step before proceeding to the next.
+- **Fail loudly:** If a step fails, surface the error immediately. Don't try to work around it silently.
+- **Scope your shell:** Prefer relative paths over absolute. Never assume a working directory without confirming it.
+
+---
+
+## 6. Context Awareness
+
+**Codex has a limited context window — use it wisely.**
+
+- Don't re-read files you've already loaded. Reference prior output instead.
+- When summarizing large codebases, compress systematically: directory tree → key files → function signatures.
+- If context is filling up, state it: *"I'm approaching context limits. Summarizing and continuing."*
+- Prefer targeted grep/search over reading entire files when looking for a specific symbol.
+
+---
+
+## 7. Tool Use Discipline
+
+**Every tool call has a cost. Make them count.**
+
+- Batch related reads into a single operation where possible.
+- Don't run the same command twice to "verify" — if you need to verify, define the assertion first.
+- Avoid speculative exploration ("let me just check...") — know what you're looking for before you look.
+- If a tool fails, diagnose before retrying. Don't brute-force.
+
+---
+
+## ✅ These guidelines are working if:
+
+- Diffs contain fewer unnecessary changes
+- Fewer rewrites due to overcomplication
+- Clarifying questions come **before** implementation, not after mistakes
+- Agentic runs complete tasks end-to-end without silent failures or scope creep

package/README.md

@@ -0,0 +1,173 @@
+# Codex-Arsenal
+
+> OpenAI Codex / Claude Code 기반 개발 경험을 극대화하기 위한  
+> 플러그인 · 스킬 · 워크플로 · 설정 · 프롬프트 큐레이션 레포지토리.
+
+---
+
+## 🧭 이 레포는 무엇인가?
+
+**Codex-Arsenal**은 AI 코딩 에이전트(OpenAI Codex, Claude Code 등)를 실무에 적용하면서  
+"vanilla setup만으로는 부족하다"고 느낀 개발자들을 위한 실용 자료 모음입니다.
+
+단순한 awesome list와 다른 점:
+
+- 실제로 써봤거나, 체감 생산성이 검증된 것만 수록
+- setup → 사용법 → 주의사항까지 한 곳에서 해결
+- 개인 개발자 / 소규모 팀 모두를 대상으로 함
+- Claude Code 스타일의 agentic workflow에 최적화
+
+> **대상 독자:** 이미 Codex 또는 Claude Code를 써본 개발자.  
+> AI 코딩 도구가 처음이라면 [공식 문서](https://platform.openai.com/docs/guides/code)부터 시작하세요.
+
+---
+
+## 📂 레포지토리 구조
+
+```
+codex-arsenal/
+├── plugins/          # 에이전트 기능을 확장하는 플러그인 모음
+├── skills/           # 재사용 가능한 에이전트 스킬 패키지
+├── prompts/          # 프롬프트 템플릿 및 system prompt 예제
+├── workflows/        # 워크플로 정의 및 실행 스크립트
+├── configs/          # .codex, VSCode, zsh, tmux 등 설정 파일
+├── references/       # 논문 · 블로그 · 주목할 GitHub 레포 링크
+├── examples/         # 실전 데모 및 before/after 예제
+└── README.md
+```
+
+---
+
+## ✨ 수록 콘텐츠 카테고리
+
+### 🔌 Plugins
+
+에이전트 자체 기능을 보강하는 플러그인.
+
+현재 수록 중 / 예정:
+
+| 이름 | 설명 | 상태 |
+|------|------|------|
+| context-window-compressor | 긴 대화 컨텍스트를 압축해 토큰 절약 | 준비 중 |
+| git-diff-helper | PR diff 요약 및 리뷰 요청 자동화 | 준비 중 |
+| multi-agent-router | 여러 에이전트에 작업을 분배하는 라우터 | 계획 중 |
+| repo-memory | 프로젝트 구조를 기억하는 메모리 레이어 | 계획 중 |
+
+---
+
+### 🧠 Skills
+
+반복 작업에서 즉시 꺼내 쓸 수 있는 스킬셋.
+
+| 스킬 | 설명 |
+|------|------|
+| `debug-workflow` | 에러 로그 → 원인 분석 → 수정 → 재현 테스트까지 파이프라인화 |
+| `pr-reviewer` | PR diff를 받아 리뷰 코멘트를 자동 생성 |
+| `test-gen` | 함수 시그니처와 코드를 보고 유닛 테스트 자동 생성 |
+| `refactor-pipeline` | 코드 품질 분석 → 리팩터링 제안 → 적용까지 단계 처리 |
+| `doc-gen` | 코드베이스에서 README, API 문서 자동 작성 |
+| `arch-analysis` | 레포 전체 구조를 분석해 의존성 맵 생성 |
+
+---
+
+### ⚙️ Configs
+
+실제 사용 중인 설정 파일 모음. 복붙 후 바로 사용 가능한 형태로 제공.
+
+- `.codex/config.json` — Codex 에이전트 기본 설정 프리셋
+- `settings.json` — VSCode + Codex 통합 설정
+- `system-prompts/` — 역할별 system prompt 템플릿 (solo dev / 팀 / 레거시 분석)
+- `.zshrc` 스니펫 — Codex CLI alias 및 단축키 모음
+- `tmux.conf` — AI 세션을 병렬로 띄우기 위한 tmux 레이아웃
+
+---
+
+### 🧩 Workflows
+
+"어떻게 써야 잘 쓰는가"에 대한 실전 운영 방식.
+
+| 워크플로 | 대상 | 핵심 아이디어 |
+|----------|------|---------------|
+| `solo-dev-loop` | 혼자 개발하는 개발자 | 계획 → 코딩 → 테스트 → 커밋을 에이전트와 함께 |
+| `startup-mvp` | 빠른 프로토타입이 필요한 팀 | 스펙 → 구현 → 배포 최단 경로 |
+| `legacy-onboarding` | 오래된 코드베이스 합류 | 에이전트로 구조 파악 → 코드 맵 생성 |
+| `ai-pair-programming` | 주니어/미드 개발자 | 에이전트를 시니어처럼 활용하는 패턴 |
+| `multi-agent-orch` | 복잡한 대형 태스크 | 여러 에이전트에게 역할 분배 후 결과 통합 |
+
+---
+
+### 📚 References
+
+읽어볼 가치 있는 자료 큐레이션. 링크만 나열하지 않고, **왜 읽어야 하는지** 한 줄 설명 포함.
+
+- 논문 · 연구 자료
+- 주목할 GitHub 레포 (with star 기준 및 실용성 코멘트)
+- 블로그 · 튜토리얼 (검증된 것만)
+- 프롬프트 엔지니어링 컬렉션
+
+---
+
+## ⭐ 수록 기준
+
+모든 콘텐츠는 아래 기준을 만족해야 합니다:
+
+| 기준 | 설명 |
+|------|------|
+| ✅ 실사용 검증 | 실제로 사용해봤거나, 커뮤니티에서 반복 검증된 것 |
+| ✅ 실무 적용 가능 | 장난감 예제가 아닌 실제 코드베이스에 적용 가능 |
+| ✅ 반복 사용성 | 한 번만 쓰고 마는 것이 아닌, 루틴으로 쓸 수 있는 것 |
+| ✅ setup 대비 효율 | 설치/설정 비용보다 얻는 생산성이 명확히 큰 것 |
+| ✅ 한계 보완 | Codex/Claude Code의 알려진 약점을 보완하는 것 |
+
+---
+
+## 🛠 빠른 시작
+
+```bash
+# 레포 클론
+git clone https://github.com/your-username/codex-arsenal.git
+cd codex-arsenal
+
+# 설정 파일 적용 (예시: VSCode 설정)
+cp configs/vscode/settings.json ~/.vscode/settings.json
+
+# 워크플로 스크립트 실행 (예시: solo-dev-loop)
+./workflows/solo-dev-loop/setup.sh
+```
+
+> 각 폴더에는 독립적인 `README.md`가 있어 개별 설치 및 사용법을 안내합니다.
+
+---
+
+## 🤝 기여 방법
+
+좋은 자료가 있다면 PR로 기여해주세요. 특히 환영하는 기여:
+
+- 실제로 오래 써서 검증된 것
+- before / after 생산성 차이가 명확한 것
+- setup 과정이 step-by-step으로 정리된 것
+- 특정 상황(레거시, 대형 레포, 팀 협업 등)에서 효과적인 것
+
+**기여 절차:**
+
+1. `fork` → feature 브랜치 생성 (`feat/plugin-이름` 또는 `feat/workflow-이름`)
+2. 해당 카테고리 폴더에 파일 추가 (각 폴더의 `TEMPLATE.md` 참고)
+3. PR 제목에 카테고리 명시: `[plugin] context-window-compressor 추가`
+4. PR 본문에 **사용 배경 / 실제 효과 / 주의사항** 포함
+
+---
+
+## 🌌 방향성
+
+가까운 미래의 개발 환경은 "IDE + 자동완성 AI" 수준을 넘어,  
+개발자가 **여러 AI 에이전트를 orchestration하며 일하는 구조**에 가까워질 것입니다.
+
+이 레포는 그 방향으로의 전환을 실험하고,  
+실제로 쓸 수 있는 도구와 패턴을 기록하는 공간입니다.
+
+---
+
+## 📌 태그
+
+`codex` `claude-code` `ai-agent` `developer-tools` `prompt-engineering`  
+`llm-workflow` `productivity` `automation` `vscode` `terminal`

package/bin/cli.js

@@ -0,0 +1,85 @@
+#!/usr/bin/env node
+import { MANIFEST, findManifestItems } from "../lib/manifest.js";
+import { runInit } from "../lib/installer.js";
+
+function printHelp() {
+  console.log(`codex-arsenal
+
+Usage:
+  codex-arsenal init [--yes] [--dir <path>]
+  codex-arsenal list
+  codex-arsenal get <id...> [--dir <path>]
+`);
+}
+
+function readOption(args, name, fallback = undefined) {
+  const index = args.indexOf(name);
+  if (index === -1) {
+    return fallback;
+  }
+  return args[index + 1] || fallback;
+}
+
+function nonOptionArgs(args) {
+  const result = [];
+  for (let index = 0; index < args.length; index += 1) {
+    const arg = args[index];
+    if (arg === "--dir" || arg === "-d") {
+      index += 1;
+      continue;
+    }
+    if (arg === "--yes" || arg === "-y") {
+      continue;
+    }
+    result.push(arg);
+  }
+  return result;
+}
+
+function printList() {
+  let currentCategory = "";
+  for (const item of MANIFEST) {
+    if (item.category !== currentCategory) {
+      currentCategory = item.category;
+      console.log(`\n${currentCategory}`);
+    }
+    console.log(`  ${item.id.padEnd(32)} ${item.description}`);
+  }
+  console.log();
+}
+
+async function main(argv) {
+  const [command = "init", ...args] = argv;
+  const dir = readOption(args, "--dir", readOption(args, "-d", process.cwd()));
+
+  if (command === "help" || command === "--help" || command === "-h") {
+    printHelp();
+    return;
+  }
+
+  if (command === "list") {
+    printList();
+    return;
+  }
+
+  if (command === "get") {
+    const ids = nonOptionArgs(args);
+    if (!ids.length) {
+      throw new Error("get requires at least one item id");
+    }
+    await runInit({ preSelected: findManifestItems(ids), skipPrompt: true, dir });
+    return;
+  }
+
+  if (command === "init") {
+    await runInit({ yes: args.includes("--yes") || args.includes("-y"), dir });
+    return;
+  }
+
+  throw new Error(`Unknown command: ${command}`);
+}
+
+main(process.argv.slice(2)).catch((error) => {
+  console.error(error.message);
+  process.exitCode = 1;
+});

package/configs/codex/config.json

@@ -0,0 +1,6 @@
+{
+  "defaultModel": "gpt-5-codex",
+  "approvalMode": "on-request",
+  "sandboxMode": "workspace-write",
+  "notes": "Starter Codex configuration. Adjust model and approvals per project."
+}

package/configs/vscode/settings.json

@@ -0,0 +1,5 @@
+{
+  "editor.formatOnSave": true,
+  "files.trimTrailingWhitespace": true,
+  "chat.agent.enabled": true
+}

package/lib/fetcher.js

@@ -0,0 +1,31 @@
+import https from "node:https";
+
+const REDIRECT_CODES = new Set([301, 302, 303, 307, 308]);
+
+export function fetchFile(url) {
+  return new Promise((resolve, reject) => {
+    https
+      .get(url, (res) => {
+        if (REDIRECT_CODES.has(res.statusCode) && res.headers.location) {
+          const nextUrl = new URL(res.headers.location, url).toString();
+          res.resume();
+          fetchFile(nextUrl).then(resolve, reject);
+          return;
+        }
+
+        if (res.statusCode !== 200) {
+          res.resume();
+          reject(new Error(`HTTP ${res.statusCode} for ${url}`));
+          return;
+        }
+
+        res.setEncoding("utf8");
+        let data = "";
+        res.on("data", (chunk) => {
+          data += chunk;
+        });
+        res.on("end", () => resolve(data));
+      })
+      .on("error", reject);
+  });
+}

package/lib/installer.js

@@ -0,0 +1,89 @@
+import { mkdir, readFile, writeFile } from "node:fs/promises";
+import { createInterface } from "node:readline/promises";
+import { stdin as input, stdout as output } from "node:process";
+import path from "node:path";
+import { BASE_URL, MANIFEST } from "./manifest.js";
+import { fetchFile } from "./fetcher.js";
+
+async function readSourceFile(src) {
+  try {
+    return await readFile(src, "utf8");
+  } catch (error) {
+    if (error.code !== "ENOENT") {
+      throw error;
+    }
+    return fetchFile(`${BASE_URL}/${src}`);
+  }
+}
+
+export async function installItems(items, targetDir) {
+  const resolvedTarget = path.resolve(targetDir);
+  let installed = 0;
+  let failed = 0;
+  const failures = [];
+
+  for (const item of items) {
+    for (const file of item.files) {
+      const destination = path.join(resolvedTarget, file.dest);
+      try {
+        const content = await readSourceFile(file.src);
+        await mkdir(path.dirname(destination), { recursive: true });
+        await writeFile(destination, content, "utf8");
+        installed += 1;
+      } catch (error) {
+        failed += 1;
+        failures.push({ item: item.id, file: file.src, error: error.message });
+      }
+    }
+  }
+
+  return { installed, failed, failures, targetDir: resolvedTarget };
+}
+
+function defaultItems() {
+  return MANIFEST.filter((item) => item.default);
+}
+
+async function askForItems(preSelected = defaultItems()) {
+  const rl = createInterface({ input, output });
+  try {
+    console.log("\nInstallable Codex-Arsenal items:\n");
+    MANIFEST.forEach((item, index) => {
+      const checked = preSelected.some((selected) => selected.id === item.id) ? "*" : " ";
+      console.log(`${String(index + 1).padStart(2, " ")}. [${checked}] ${item.id} - ${item.description}`);
+    });
+    const answer = await rl.question("\nChoose item numbers separated by commas, or press Enter for defaults: ");
+    if (!answer.trim()) {
+      return preSelected;
+    }
+
+    const selectedIndexes = answer
+      .split(",")
+      .map((part) => Number(part.trim()) - 1)
+      .filter((index) => Number.isInteger(index) && MANIFEST[index]);
+
+    return selectedIndexes.map((index) => MANIFEST[index]);
+  } finally {
+    rl.close();
+  }
+}
+
+export async function runInit(opts = {}) {
+  const selected = opts.skipPrompt || opts.yes
+    ? opts.preSelected || defaultItems()
+    : await askForItems(opts.preSelected || defaultItems());
+
+  if (!selected.length) {
+    console.log("No items selected.");
+    return { installed: 0, failed: 0, failures: [], targetDir: path.resolve(opts.dir || ".") };
+  }
+
+  const result = await installItems(selected, opts.dir || process.cwd());
+  for (const item of selected) {
+    for (const file of item.files) {
+      console.log(`installed ${file.dest}`);
+    }
+  }
+  console.log(`\nDone: ${result.installed} installed${result.failed ? `, ${result.failed} failed` : ""}.`);
+  return result;
+}

package/lib/manifest.js

@@ -0,0 +1,93 @@
+export const REPO = "your-username/codex-arsenal";
+export const BRANCH = "main";
+export const BASE_URL = `https://raw.githubusercontent.com/${REPO}/${BRANCH}`;
+
+export const MANIFEST = [
+  {
+    id: "codex-md",
+    category: "Behavior Guidelines",
+    label: "CODEX.md",
+    description: "Behavior guidelines for Codex agents in software projects.",
+    files: [{ src: "CODEX.md", dest: "CODEX.md" }],
+    default: true
+  },
+  {
+    id: "claude-md",
+    category: "Behavior Guidelines",
+    label: "CLAUDE.md",
+    description: "Behavior guidelines adapted for Claude Code agents.",
+    files: [{ src: "CLAUDE.md", dest: "CLAUDE.md" }]
+  },
+  {
+    id: "config-codex",
+    category: "Configs",
+    label: ".codex/config.json",
+    description: "Starter Codex agent configuration.",
+    files: [{ src: "configs/codex/config.json", dest: ".codex/config.json" }]
+  },
+  {
+    id: "config-vscode",
+    category: "Configs",
+    label: ".vscode/settings.json",
+    description: "VS Code settings for AI-assisted development.",
+    files: [{ src: "configs/vscode/settings.json", dest: ".vscode/settings.json" }]
+  },
+  {
+    id: "prompt-solo-dev",
+    category: "Prompts",
+    label: "solo-dev system prompt",
+    description: "System prompt template for solo developer workflows.",
+    files: [{ src: "prompts/system-prompts/solo-dev.md", dest: "prompts/system-prompts/solo-dev.md" }]
+  },
+  {
+    id: "skill-debug-workflow",
+    category: "Skills",
+    label: "debug-workflow",
+    description: "A repeatable skill for reproducing, diagnosing, and fixing bugs.",
+    files: [
+      { src: "skills/debug-workflow/README.md", dest: "skills/debug-workflow/README.md" },
+      { src: "skills/debug-workflow/prompt.md", dest: "skills/debug-workflow/prompt.md" },
+      { src: "skills/debug-workflow/workflow.json", dest: "skills/debug-workflow/workflow.json" }
+    ]
+  },
+  {
+    id: "skill-test-gen",
+    category: "Skills",
+    label: "test-gen",
+    description: "A skill for generating focused tests from function signatures and behavior notes.",
+    files: [
+      { src: "skills/test-gen/README.md", dest: "skills/test-gen/README.md" },
+      { src: "skills/test-gen/prompt.md", dest: "skills/test-gen/prompt.md" }
+    ]
+  },
+  {
+    id: "plugin-context-window-compressor",
+    category: "Plugins",
+    label: "context-window-compressor",
+    description: "Plugin sketch for summarizing long context before it becomes unmanageable.",
+    files: [
+      { src: "plugins/context-window-compressor/README.md", dest: "plugins/context-window-compressor/README.md" },
+      { src: "plugins/context-window-compressor/plugin.json", dest: "plugins/context-window-compressor/plugin.json" }
+    ]
+  },
+  {
+    id: "workflow-solo-dev-loop",
+    category: "Workflows",
+    label: "solo-dev-loop",
+    description: "Plan, code, test, and commit loop for solo developers working with agents.",
+    files: [
+      { src: "workflows/solo-dev-loop/README.md", dest: "workflows/solo-dev-loop/README.md" },
+      { src: "workflows/solo-dev-loop/setup.sh", dest: "workflows/solo-dev-loop/setup.sh" }
+    ]
+  }
+];
+
+export function findManifestItems(ids) {
+  return ids.map((id) => {
+    const item = MANIFEST.find((entry) => entry.id === id);
+    if (!item) {
+      throw new Error(`Unknown item: ${id}`);
+    }
+    return item;
+  });
+}

package/package.json

@@ -0,0 +1,45 @@
+{
+  "name": "codex-arsenal",
+  "version": "0.1.0",
+  "description": "A practical arsenal of Codex and Claude Code plugins, skills, prompts, workflows, and configs.",
+  "type": "module",
+  "bin": {
+    "codex-arsenal": "bin/cli.js"
+  },
+  "scripts": {
+    "test": "node --test"
+  },
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/citron03/Codex-Arsenal.git"
+  },
+  "bugs": {
+    "url": "https://github.com/citron03/Codex-Arsenal/issues"
+  },
+  "homepage": "https://github.com/citron03/Codex-Arsenal#readme",
+  "publishConfig": {
+    "access": "public"
+  },
+  "files": [
+    "bin/",
+    "lib/",
+    "CODEX.md",
+    "CLAUDE.md",
+    "configs/",
+    "plugins/",
+    "prompts/",
+    "skills/",
+    "workflows/"
+  ],
+  "engines": {
+    "node": ">=18"
+  },
+  "keywords": [
+    "codex",
+    "claude-code",
+    "ai-agent",
+    "developer-tools",
+    "prompt-engineering"
+  ],
+  "license": "MIT"
+}

package/plugins/context-window-compressor/README.md

@@ -0,0 +1,7 @@
+# context-window-compressor
+
+Plugin sketch for compressing long coding-session context into a compact handoff.
+
+## Goal
+
+Preserve decisions, open questions, changed files, commands run, and verification status while removing repetitive exploration details.

package/plugins/context-window-compressor/plugin.json

@@ -0,0 +1,6 @@
+{
+  "name": "context-window-compressor",
+  "version": "0.1.0",
+  "description": "Summarizes long agent context into a concise continuation note.",
+  "entry": "README.md"
+}

package/prompts/system-prompts/solo-dev.md

@@ -0,0 +1,11 @@
+# Solo Developer Agent Prompt
+
+You are helping a solo developer move from idea to shipped change.
+
+Work loop:
+
+1. Restate the goal and assumptions.
+2. Inspect the existing project before editing.
+3. Make the smallest useful change.
+4. Run focused verification.
+5. Report what changed, what was verified, and what remains risky.

package/skills/debug-workflow/README.md

@@ -0,0 +1,12 @@
+# debug-workflow
+
+A repeatable debugging skill for agentic coding sessions.
+
+## Steps
+
+1. Reproduce the symptom with the smallest command or test.
+2. Capture the actual error output.
+3. Identify the boundary where expected behavior first diverges.
+4. Add or update a regression test.
+5. Implement the smallest fix.
+6. Re-run the regression test and the nearest relevant suite.

package/skills/debug-workflow/prompt.md

@@ -0,0 +1,3 @@
+You are debugging a software issue. Do not patch first.
+
+Start by reproducing the failure, then state the observed behavior, expected behavior, and the narrowest suspected boundary. Add a regression test before changing production code.

package/skills/debug-workflow/workflow.json

@@ -0,0 +1,11 @@
+{
+  "name": "debug-workflow",
+  "version": "0.1.0",
+  "steps": [
+    "reproduce",
+    "inspect",
+    "write-regression-test",
+    "fix",
+    "verify"
+  ]
+}

package/skills/test-gen/README.md

@@ -0,0 +1,15 @@
+# test-gen
+
+A skill for turning behavior notes and function signatures into focused tests.
+
+## Inputs
+
+- Function or module path
+- Expected behavior
+- Edge cases worth preserving
+
+## Output
+
+- Minimal tests that use real code
+- Clear test names
+- Assertions that describe behavior, not implementation details

package/skills/test-gen/prompt.md

@@ -0,0 +1 @@
+Generate tests before implementation. Prefer one behavior per test. Use real code unless a dependency is external, slow, or nondeterministic.

package/workflows/solo-dev-loop/README.md

@@ -0,0 +1,12 @@
+# solo-dev-loop
+
+A practical loop for solo developers working with coding agents.
+
+## Loop
+
+1. Define the next verifiable goal.
+2. Ask the agent to inspect the local project.
+3. Write or update a focused test.
+4. Implement the smallest change.
+5. Run verification.
+6. Commit the finished slice.

package/workflows/solo-dev-loop/setup.sh

@@ -0,0 +1,5 @@
+#!/usr/bin/env sh
+set -eu
+
+mkdir -p .codex prompts workflows
+printf '%s\n' "solo-dev-loop assets copied. Review CODEX.md and project prompts before use."