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.
npx skills add hashgraph-online/awesome-codex-plugins --skill agent-dev-workshopgit clone --depth 1 https://github.com/hashgraph-online/awesome-codex-pluginsWrote 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.
[](https://agentmods.dev/skills/hashgraph-online/awesome-codex-plugins/agent-dev-workshop)<a href="https://agentmods.dev/skills/hashgraph-online/awesome-codex-plugins/agent-dev-workshop"><img src="https://agentmods.dev/badge/skills/hashgraph-online/awesome-codex-plugins/agent-dev-workshop.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00099 | $0.03436 |
| Opus 5 | $0.00049 | $0.01718 |
| Sonnet 5 | $0.00020 | $0.00687 |
| Haiku 4.5 | $0.00010 | $0.00344 |
Grade A, and why
agent-dev-workshop 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.
How it starts
The opening of the file, as written. The whole thing — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Dev Workshop
交互式 AI Agent 开发工作坊。用户通过深度协作式对话，逐阶段完成 Agent 设计并生成可直接运行的项目代码。
何时激活
- 用户说"开发 agent"、"创建 agent"、"构建 agent"、"agent 开发"
- 用户要基于 EINO / LangChain / AutoGen / AgentScope / CrewAI 创建 Agent 应用
- 用户要将已有 Agent 迁移到另一个框架
- 用户说"agent dev"、"build agent"、"create agent"、"develop agent"
/agent-dev命令入口
三种运行模式
默认模式（深度协作）
完整 6 阶段交互流程。每个阶段结束必须用户确认后才推进到下一阶段，每个工具/组件逐一交互确认。
快速模式（--quick）
用户给一句话需求 → 自动执行 Phase 1-4（推断 Agent 类型、匹配架构模式、生成默认工具和 Prompt）→ 仅在 Phase 5 代码生成后做一次整体确认 → Phase 6 验证。适合有经验用户或原型快速验证。
快速模式约束：
- 自动推断时，选择最常见的默认值（如：单 Agent 默认 ReAct，多角色默认 Multi-Agent Conversation）
- 框架选择依据用户指定语言自动匹配（Python → LangChain，Go → EINO，未指定 → LangChain）
- 生成后必须完整展示项目结构和核心文件内容，等待用户确认
导入模式（--import）
用户指定已有 Agent 代码路径：
- 分析现有代码：识别框架、Agent 类型、工具列表、Prompt、编排逻辑
- 生成
agent-spec.md（逆向提取）— 展示给用户确认 - 用户确认：确认提取结果 + 选择目标框架
- 跳转 Phase 5：用目标框架重新生成代码
- Phase 6：对比验证原 Agent 行为是否保留
导入模式约束：
- 必须列出代码分析中的不确定项，让用户确认
- 原 Agent 的所有工具必须在新框架中保留等效实现
- 生成 diff 摘要：原框架 vs 目标框架的关键差异
严格约束
- 每个阶段必须用户确认后才能进入下一阶段。严禁静默推进。
- 每个阶段开始前，先读取
references/phase{N}-*.md获取该阶段详细指引。 - 遇到需求冲突或不明确的约束，立即暂停并提问，不自行推测。
- 每个阶段的核心产出必须立即写入磁盘，不允许仅停留在对话上下文中。
- 代码生成阶段（Phase 5），必须读取
adk-framework-adapters对应框架的 reference 文件后再生成代码。 - 框架适配 reference 文件标注了
verified_date，若距今超过 90 天，应提醒用户 API 可能已变化。
工作方式
- 阶段驱动：按 Phase 1 → 6 顺序推进，每阶段有明确的输入、活动、产出和确认点。
- 追踪表：在 Phase 1 结束后创建
{output_dir}/tracking.md，每个阶段完成后更新状态。 - 引用 reference：每个阶段开始前，读取对应
references/phase{N}-*.md获取详细引导。 - 立即落盘：每个阶段的产出文件在完成后立即写入
{output_dir}/，并展示给用户确认。 - 跨 skill 调用：Phase 2 调用
agent-patterns-catalog匹配架构模式；Phase 5 调用adk-framework-adapters加载框架模板。
阶段概览
| Phase | 名称 | 核心活动 | 产出文件 | Reference |
|---|---|---|---|---|
| 1 | 需求发现 | 业务场景、Agent 类型、框架、约束 | agent-spec.md |
references/phase1-discovery.md |
| 2 | 架构设计 | 架构模式匹配、组件拓扑、数据流 | agent-architecture.md |
references/phase2-architecture.md |
| 3 | 工具与能力 | 工具定义、Memory 策略、RAG pipeline | agent-tools.md |
references/phase3-tools.md |
| 4 | Prompt 与编排 | System Prompt、编排逻辑、路由策略 | agent-prompts.md + agent-orchestration.md |
references/phase4-prompts.md |
| 5 | 代码生成 | 框架代码、项目结构、配置、脚本 | 完整项目目录 | references/phase5-codegen.md |
| 6 | 验证迭代 | 依赖安装、测试、Smoke Test、迭代 | 验证报告 | references/phase6-verification.md |
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago First seen · 297 lines · 99 tokens per session scan A 8baa93e5d4ab
agent-dev-workshop is a skill published in the GitHub repository hashgraph-online/awesome-codex-plugins (956 stars, last pushed today), licensed Apache-2.0. It adds 99 tokens to every session and 3,436 once invoked, about $0.0005 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 2026-09-05.
Other skills, from other repositories
search
Search 2500+ curated ChatGPT and LLM open-source repositories. Use when the user asks to find tools, libraries, or repos related to ChatGPT, LLMs, RAG, agents, langchain, NLP, AI development, or any open-source AI tooling.
sprr
Single PR reviewer for awesome-quant. Use when the user asks to review, validate, comment on, label, close, or merge one specific pull request that adds README.md entries. Triggers include "sprr", "review PR", "check PR", and "validate contribution".
bprr
Bulk PR reviewer for awesome-quant. Use when the user asks to review all open PRs, review unreviewed PRs, bulk review, or mentions "bprr". Reviews open PRs lacking the reviewed label and presents a summary before any merge/comment/label action.
drawio-reconstruction
Reconstructs reference images into high-fidelity, editable Draw.io files with rendered previews: native Draw.io elements carry text and structure, SVG covers simple icons that match the reference, and cropped or transparent PNGs preserve complex visuals. Use when the user wants a diagram image, research figure…
benchmark-paper-template
Structures Benchmark and Evaluation papers using the five-pillar framework (Research Gap, Construction Pipeline, Evaluation Framework, Empirical Findings, optional Companion Method). Returns a completeness audit, a six-part Introduction logic chain, a Section 2-7 skeleton, and a pre-submission checklist. Use when…
reverse-engineering-android-malware-with-jadx
Reverse engineers malicious Android APK files using JADX decompiler to analyze Java/Kotlin source code, identify malicious functionality including data theft, C2 communication, privilege escalation, and overlay attacks. Examines manifest permissions, receivers, services, and native libraries. Activates for requests…