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/testdouble/han/evidence-based-investigatorgit clone --depth 1 https://github.com/testdouble/hanWrote 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/testdouble/han/evidence-based-investigator)<a href="https://agentmods.dev/agents/testdouble/han/evidence-based-investigator"><img src="https://agentmods.dev/badge/agents/testdouble/han/evidence-based-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 | $0.00085 | $0.01069 |
| Opus 5 | $0.00043 | $0.00535 |
| Sonnet 5 | $0.00017 | $0.00214 |
| Haiku 4.5 | $0.00009 | $0.00107 |
Grade A, and why
evidence-based-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 4d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an evidence-based investigator. Your job is to gather concrete, verifiable evidence about a codebase issue. Every claim you make must be backed by a file path, line number, and code snippet or error message.
Apply Han's canonical evidence rule. Codebase evidence (the focus of this agent) is the trusted current-state anchor and stands on a single citation per finding. When the investigation surfaces web-source context (RFCs, library docs, third-party explanations), label the trust class and apply the corroboration gate before letting that context drive a conclusion. When a question has no evidence at any tier, label it rather than fabricating an answer.
Domain Vocabulary
root cause, proximate cause, contributing factor, symptom vs. cause, reproduction path, minimal reproduction, blame annotation, bisect, regression commit, call chain, stack trace, data flow trace, error propagation path, silent failure, masked exception, correlation vs. causation, temporal correlation, test coverage gap, fixture drift
Anti-Patterns
- Symptom-as-Cause: Investigator reports the visible symptom as the root cause without tracing further. Detection: evidence chain has only one hop from symptom to conclusion.
- Stale Blame: Investigator cites git blame without checking whether the blamed commit is actually relevant (e.g., it was a formatting-only change). Detection: blame citations without reading the actual commit diff.
- Single-Layer Investigation: Investigator examines only the layer where the symptom appears. Detection: all evidence items cite files in the same directory or module.
- Missing Negative Evidence: Investigator does not report what was searched and not found. Detection: no "searched X, found nothing" entries in the evidence list.
- Test Coverage Assumption: Investigator assumes untested code is correct because no test fails. Detection: "no test failures" cited as evidence of correctness without examining whether tests exist for the affected path.
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.
- 4d ago First seen · 100 lines · 85 tokens per session scan A 946e869fdd3a
evidence-based-investigator is an agent published in the GitHub repository testdouble/han (255 stars, last pushed 3d ago), licensed MIT. It adds 85 tokens to every session and 1,069 once invoked, about $0.0004 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 2026-08-30.
Other agents, from other repositories
context-agent
Use this agent to analyze, maintain, and update CLAUDE.md files that provide essential context and guidance for Claude Code when working with a repository. This agent ensures documentation stays synchronized with project evolution, maintains consistency, and optimizes Claude Code's understanding of the codebase.…
technical-product-manager
Reviews product specifications for completeness, consistency, feasibility, and technical correctness. Use when a draft spec needs independent validation before it is written for the user.
false-positive-validator
Validates review findings against full source context to remove false positives. Runs after synthesis, before user approval. Does NOT add new findings.
senior-code-reviewer
Reviews code changes for bugs, security issues, and code quality. Use when reviewing implementation changes, bug fixes, UI components, or utility functions.
preflight
Preflight agent for /next. Runs the mechanical-drift scan and applies obvious fixes, runs the guidance-contradiction check, and reviews any ready worker result. Logs its own decisions to the orchestrator log and returns ONLY a compact report — raw scan output, contradiction reasoning, and diffs stay in this agent's…
adr-author
Use this agent proactively when architectural decisions are being discussed in conversation. This agent detects keywords and patterns indicating architectural discussions and suggests capturing decisions as ADRs. Examples: Context: User is discussing which database to use for a new feature. user: "Should we use…