expert-bootstrap

expert-bootstrap is a skill for Claude Code, Codex from TashanGKD/tashan-cursor-skills. It costs 103 tokens per session (3,659 once invoked), scanned A, original, MIT.

A workflow for training a specialised agent to review work in a particular subject area. It combines outside research, internal documents, project inspection, reflection, and an expert configuration.

In plain words
What is it for?
It is for building review agents for areas such as programming performance, agent security, architecture, prompt design, or test reports.
Why use it?
It addresses cases where the available reviewer lacks enough subject knowledge. The resulting configuration gives an agent a defined basis for making informed reviews.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit It is for building review agents for areas such as programming performance, agent security, architecture, prompt design, or test reports.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tashangkd/tashan-cursor-skills/expert-bootstrap
Install

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.

Any agent
npx skills add TashanGKD/tashan-cursor-skills --skill expert-bootstrap
Clone the repo
git clone --depth 1 https://github.com/TashanGKD/tashan-cursor-skills

Made for: Claude Code, Codex.

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 expert-bootstrap

README.md
[![agentmods](https://agentmods.dev/badge/skills/tashangkd/tashan-cursor-skills/expert-bootstrap/github.svg)](https://agentmods.dev/skills/tashangkd/tashan-cursor-skills/expert-bootstrap)
Your own site
<a href="https://agentmods.dev/skills/tashangkd/tashan-cursor-skills/expert-bootstrap"><img src="https://agentmods.dev/badge/skills/tashangkd/tashan-cursor-skills/expert-bootstrap/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 expert-bootstrap

Your own site · 80×15
<a href="https://agentmods.dev/skills/tashangkd/tashan-cursor-skills/expert-bootstrap"><img src="https://agentmods.dev/badge/skills/tashangkd/tashan-cursor-skills/expert-bootstrap.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,659 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00103 $0.03659
Opus 5 $0.00051 $0.01829
Sonnet 5 $0.00021 $0.00732
Haiku 4.5 $0.00010 $0.00366

Measured 9d ago against content hash 91926ae9f345, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

expert-bootstrap 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.

skills/expert-bootstrap/SKILL.md · 322 lines

How it starts

The opening of the file, as written. The whole thing — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Expert Bootstrap:按需专家培养范式

关系类型:implements → 多智能体框架全景导航_v1.0.md(场景一:多专家讨论闭环) 核心洞见:TYPE-R 产出的是「知识给 CEO 用」(K-object → 知识库); expert-bootstrap 产出的是「知识让 Agent 成为专家」(B-object → Agent 定义文件)。 两者目标不同,不可混用。


我是谁

你被激活后,将执行一个通用专家培养流程,目标是:

  1. 深入理解某个领域的最佳实践
  2. 对标当前项目的实际状况
  3. 通过自问自答反思建立真正的专家视角
  4. 产出一个可被 Orchestrator 直接 dispatch 的专家 Agent 定义文件

产出的 Agent 具备:在该领域独立提出有据可查的专业意见的能力


激活后立即执行

D0 行:先确认任务范围

Read: 多智能体框架全景导航_v1.0.md(确认专家培养在哪个闭环里)
询问(如果 Orchestrator 没有在简报里指定):
  □ 目标领域是什么?(如:「Python 并发性能优化」「AI Agent 安全审查」)
  □ 待审查的项目是什么?(路径或描述)
  □ 这个专家最终要审查什么产出物?(代码/架构文档/Prompt设计/测试报告)
  □ 专家需要持久化吗?(是 → 写入 Agent 定义文件;否 → 只用于本次任务)

四阶段执行流程

Phase 1:调研(Research)

目标:建立领域全景知识,重点关注最佳实践和常见陷阱

Step 1.1【外部调研】
  → WebSearch 5-8 次:
    搜索词模式:
    - "[领域] best practices 2025 2026"
    - "[领域] common mistakes anti-patterns"
    - "[具体技术栈] [领域] production experience"
    - "[领域] code review checklist"
  → WebFetch:获取最高质量的 3-5 篇原文内容
  → 记录:每篇来源的核心观点(不超过 5 条)

Step 1.2【内部调研】
  → 搜索已有知识库:
    rg "[领域关键词]" _内部总控/认知结构/ --include="*.md" -l
    rg "[领域关键词]" _内部总控/开发规范/ --include="*.md" -l
  → Read 命中的相关文档(摘要性阅读,不全量读取)
  → 记录:我们已有的相关知识和历史踩坑

Step 1.3【项目代码/文档阅读】
  → Read 待审查项目的核心文件(技术架构文档 + 关键模块代码)
  → 目的:了解项目的实际情况,为对标做准备
  → 记录:项目当前状况的关键事实(不评价,只描述)

Phase 1 产出物bootstrap-temp/research-summary.md

# 领域知识摘要:[领域名称]

## 外部最佳实践(来源:[URL列表])
- [关键实践 1]:[具体说明]
- [关键实践 2]:[具体说明]
...

## 常见陷阱(来自实战经验)
- [陷阱 1]:[症状] + [根因] + [解决方案]
...

## 我们已有的相关知识
- [已有文档路径]:[关键点]
...

## 项目当前状况(事实性描述)
- [观察 1]
- [观察 2]
...

Phase 2:结构化整理(Synthesis)

目标:将调研知识整理为可操作的审查框架

Step 2.1【对标差距分析】
  → 将「最佳实践」与「项目现状」逐点对比:
  
  | 最佳实践要求 | 项目当前状况 | 差距程度 | 证据来源 |
  |-------------|-------------|---------|---------|
  | [实践要求]  | [现状描述]  | ✅/⚠️/❌ | [代码行/文档位置] |

Step 2.2【审查清单生成】
  → 基于对标结果,生成可复用的「领域审查清单」:
  
  格式(每条必须具备):
  ✓ 检查项:[具体可验证的问题]
  ✓ 验证方式:[如何检查:grep/read/run/计算]
  ✓ 判断标准:[什么情况是 ✅,什么情况是 ❌]
  ✓ 严重程度:[P0/P1/P2/P3 + 理由]

Read the full file on GitHub · 322 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 · 322 lines · 103 tokens per session scan A 91926ae9f345

Subscribe to this mod's changes

expert-bootstrap is a skill published in the GitHub repository TashanGKD/tashan-cursor-skills (20 stars, last pushed 5mo ago), licensed MIT. It adds 103 tokens to every session and 3,659 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 2026-09-03.

Related

Other skills, from other repositories

android-feature

Workflow for implementing a new Android feature, screen, fragment, activity, dialog, adapter, or enhancement in this XML/MVVM template. Use whenever the user asks to add, build, implement, or extend functionality — before writing any code. Covers planning, the MVVM/MVI skeleton, the Android configuration checklist…

orbitalsonic/AndroidPilot · 72 tokens

template-helpers

Catalog of the reusable building blocks shipped with this Android template — BaseActivity/BaseFragment, the helpers/ extension files (navigation, lifecycle, toast, snackbar, dialogs, images, permissions, theme, locale, settings intents, date, delay), common/ (Firebase, network, observers), and…

orbitalsonic/AndroidPilot · 92 tokens

android-new-project

Workflow for turning a fresh copy of this Android template into a new app — renaming the package/namespace/applicationId, branding (icons, splash, palette, fonts), Firebase setup, signing config, stripping unused sample screens, and verifying the foundation. Use when the user says they are starting a new app…

orbitalsonic/AndroidPilot · 83 tokens

android-preflight

Final verification checklist to run before declaring Android work finished — build, both themes, string resources, lifecycle and leak risks, registered permissions and components, resource parity between values and values-night, and honest reporting of what was and was not verified. Use at the end of any feature, fix…

orbitalsonic/AndroidPilot · 79 tokens

android-ui-theming

Rules for Android XML layouts, Material 3 components, semantic color tokens, light/dark theming, dimensions (sdp/ssp), string resources and localization, accessibility, and edge-to-edge insets. Use when creating or editing any layout, drawable, style, color, vector, or string resource, or when a screen must work in…

orbitalsonic/AndroidPilot · 81 tokens

android-upgrade

Workflow for changing an existing working Android project — upgrading dependencies, AGP/Gradle or SDK levels, migrating deprecated APIs, refactoring, and fixing bugs, without breaking what already works. Covers baseline verification, scoping the diff, targetSdk behaviour changes, SharedPreferences/Room data…

orbitalsonic/AndroidPilot · 86 tokens