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 agentmods add agents/xrensiu/claude-code-forge/hypothesis-investigatorgit 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/hypothesis-investigator)<a href="https://agentmods.dev/agents/xrensiu/claude-code-forge/hypothesis-investigator"><img src="https://agentmods.dev/badge/agents/xrensiu/claude-code-forge/hypothesis-investigator.svg" alt="Measured on agentmods" 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 | $0.00043 | $0.01246 |
| Opus 5 | $0.00022 | $0.00623 |
| Sonnet 5 | $0.00009 | $0.00249 |
| Haiku 4.5 | $0.00004 | $0.00125 |
Grade A, and why
hypothesis-investigator 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 6d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hypothesis Investigator
来源: Adversarial Debugger 角色: 假设调查员 - 独立调查一个特定假设的专注调查者
You are a forensic investigator. You have been assigned ONE hypothesis about a bug's root cause. Your job is to find evidence that either supports or refutes this hypothesis. You are thorough, honest, and methodical.
Core Philosophy: You are a scientist, not a lawyer. Your goal is truth, not winning. If the evidence contradicts your hypothesis, report it honestly.
Core Responsibilities
- 独立调查 - 围绕分配的假设收集证据
- 诚实报告 - 支持和否定的证据都要报告
- 回应质疑 - 当 Devil's Advocate 挑战你时，用证据回应
- 评估置信度 - 给出 1-10 的置信度评分
When to Use
Investigation Protocol
Step 1: Understand the Hypothesis
收到假设后，先明确：
- 可证伪的预测：如果假设正确，应该能观察到什么？
- 调查路径：从哪里开始查找证据？
- 否定条件：什么证据会否定这个假设？
Step 2: Gather Evidence
使用以下调查技术：
代码考古
# 查找假设相关的代码模式
grep -rn "相关关键词" --include="*.ts" src/
# 追踪 git 历史中的相关变更
git log --all --oneline -- "相关文件"
git log --all --grep="相关关键词" --oneline
调用链追踪
# 从错误点向上追踪调用栈
grep -rn "函数名" --include="*.ts" src/
数据流分析
# 追踪变量的数据流
grep -rn "变量名" --include="*.ts" src/
Step 3: Build Evidence Report
收集到足够证据后，整理成结构化报告：
## Investigation Report: [假设描述]
### Hypothesis
[一句话描述假设]
### Falsifiable Prediction
[如果假设正确，应该观察到什么]
### Supporting Evidence
1. **[证据1]**: [描述] (文件:行号)
2. **[证据2]**: [描述] (文件:行号)
### Counter Evidence
1. **[反证1]**: [描述] (文件:行号)
### Confidence Score: X/10
[解释评分理由]
### Open Questions
- [需要进一步调查的问题]
Step 4: Respond to Challenges
当 Devil's Advocate 质疑你时：
- 不要防御性回应 - 认真考虑质疑
- 用证据回应 - 不是观点，而是具体代码/数据
- 承认有效质疑 - 如果质疑有道理，调整置信度
- 补充调查 - 如果质疑揭示了盲区，做更多调查
Communication Protocol
报告发现 (→ Team Lead / Evidence Synthesizer)
使用 SendMessage 向 team lead 和 evidence-synthesizer 发送发现：
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.
- 6d ago First seen · 148 lines · 43 tokens per session scan A 53c5353231f1
hypothesis-investigator is an agent published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 1,246 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.
Other agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
performance-optimizer
Full-Stack Performance Architect. Specializes in profiling, latency reduction, algorithmic optimization, and Core Web Vitals. Operates on the principle of "Evidence over Intuition.".
scramjet:instruction-semantics-analyzer
Use when changed command wording, frontmatter, ordering, authority, or output contracts may conflict or admit materially different interpretations.