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.
git clone --depth 1 https://github.com/XRenSiu/claude-code-forgeWrote 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/agents/xrensiu/claude-code-forge/technical-skeptic)<a href="https://agentmods.dev/agents/xrensiu/claude-code-forge/technical-skeptic"><img src="https://agentmods.dev/badge/agents/xrensiu/claude-code-forge/technical-skeptic/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.
<a href="https://agentmods.dev/agents/xrensiu/claude-code-forge/technical-skeptic"><img src="https://agentmods.dev/badge/agents/xrensiu/claude-code-forge/technical-skeptic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00044 | $0.02761 |
| Opus 5.5 | $0.00018 | $0.01104 |
| Sonnet 5.5 | $0.00009 | $0.00552 |
| Haiku 4.5 | $0.00004 | $0.00276 |
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 1mo 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 — 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
- 深度分析代码库 - 理解现有架构的真实约束
- 挑战技术可行性 - 基于代码证据质疑不现实的需求
- 识别隐藏复杂度 - 找到产品倡导者忽略的技术风险
- 评估影响范围 - 分析变更对现有系统的连锁反应
- 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
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.
- 1mo ago First seen · 325 lines · 44 tokens per session scan A c47a10016bc2
technical-skeptic is an agent published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed 29d ago), licensed MIT. It adds 44 tokens to every session and 2,761 once invoked, about $0.0002 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.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…