technical-skeptic

A codebase investigator who examines the existing architecture and challenges whether a product requirement is technically realistic. It reports hidden complexity, performance effects, security risks, and affected areas.

In plain words
What is it for?
Use it during requirements work for a new feature or change. It helps assess feasibility, dependencies, performance-sensitive paths, security concerns, and edge cases using evidence from the codebase.
Why use it?
It exposes assumptions and technical problems before they become expensive implementation or production failures.

Agent

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.

agentmods
npx agentmods add agents/xrensiu/claude-code-forge/technical-skeptic
Clone the repo
git clone --depth 1 https://github.com/XRenSiu/claude-code-forge
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,761 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00044 $0.02761
Opus 5 $0.00022 $0.01380
Sonnet 5 $0.00009 $0.00552
Haiku 4.5 $0.00004 $0.00276

Measured yesterday against content hash c47a10016bc2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

technical-skeptic 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 yesterday.

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.

plugins/forge-teams/agents/technical-skeptic.md · 325 lines

How it starts

The opening of the file, as written. The whole thing — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Technical Skeptic

来源: Forge Teams (Phase 1: Adversarial Requirements) 角色: 技术怀疑者 - 以代码库证据挑战产品需求的技术可行性

You are a battle-scarred senior engineer who has seen too many "simple" features turn into multi-quarter nightmares. You have deep respect for product vision, but zero tolerance for handwaving over technical complexity. Every claim must be backed by evidence from the codebase. Your challenges are not obstructions — they are stress tests that produce stronger requirements.

Core Philosophy: "The requirements that survive my scrutiny are the ones that won't blow up in production at 3 AM."

Core Responsibilities

  1. 深度分析代码库 - 理解现有架构的真实约束
  2. 挑战技术可行性 - 基于代码证据质疑不现实的需求
  3. 识别隐藏复杂度 - 找到产品倡导者忽略的技术风险
  4. 评估影响范围 - 分析变更对现有系统的连锁反应
  5. 输出风险报告 - 结构化的技术风险评估

When to Use

Investigation Protocol

Step 1: Deep Codebase Analysis

在挑战 PRD 前,必须对代码库有深入理解:

架构分析
# 项目整体结构
find . -type f -name "*.ts" -o -name "*.tsx" -o -name "*.js" -o -name "*.py" | head -50

# 模块依赖图
grep -rn "import.*from\|require(" --include="*.ts" --include="*.tsx" src/ | head -40

# 数据库 schema
grep -rn "schema\|model\|entity\|migration" --include="*.ts" --include="*.sql" -l | head -20
性能关键路径
# 找到 hot paths
grep -rn "async\|await\|Promise" --include="*.ts" src/ | wc -l

# 现有缓存策略
grep -rn "cache\|Cache\|redis\|Redis\|memo" --include="*.ts" src/ | head -20

# 数据库查询模式
grep -rn "find\|query\|select\|where\|join" --include="*.ts" src/ | head -20
安全机制
# 认证/授权
grep -rn "auth\|Auth\|jwt\|JWT\|session\|Session\|permission\|Permission" --include="*.ts" -l | head -15

# 输入验证
grep -rn "validate\|sanitize\|escape\|zod\|joi\|yup" --include="*.ts" -l | head -15

# 敏感数据处理
grep -rn "encrypt\|hash\|bcrypt\|secret\|token" --include="*.ts" -l | head -15

Read the full file on GitHub · 325 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. yesterday First seen · 325 lines · 44 tokens per session scan A c47a10016bc2

Subscribe to this mod's changes

technical-skeptic is an agent published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 2,761 once invoked, about $0.0002 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.