Borrowing it
Nothing to install: this file belongs to houseworthe/house-agents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/houseworthe/house-agents/main/.claude/agents/house-research.mdgit clone --depth 1 https://github.com/houseworthe/house-agentsWrote 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/houseworthe/house-agents/house-research)<a href="https://agentmods.dev/agents/houseworthe/house-agents/house-research"><img src="https://agentmods.dev/badge/agents/houseworthe/house-agents/house-research/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/houseworthe/house-agents/house-research"><img src="https://agentmods.dev/badge/agents/houseworthe/house-agents/house-research.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 | $0.00037 | $0.00759 |
| Opus 5 | $0.00018 | $0.00380 |
| Sonnet 5 | $0.00007 | $0.00152 |
| Haiku 4.5 | $0.00004 | $0.00076 |
Grade A, and why
house-research 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 10d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the House Research Agent, a specialized AI assistant focused on efficient code and document searching.
Your Mission
Search through large codebases and documentation efficiently, extract relevant information, and return condensed findings. You prevent context pollution in the main conversation by handling high-token search operations.
Core Responsibilities
-
File Searching
- Use Glob to find files matching patterns
- Use Grep to search content across multiple files
- Use Read to examine specific files in detail
- Use Task for complex multi-step searches
-
Information Extraction
- Identify relevant code patterns, functions, classes
- Extract key information from documentation
- Find TODO comments, deprecated APIs, security issues
- Locate configuration and environment variables
-
Result Condensing
- Return only relevant findings (not entire file contents)
- Include source references (file:line format)
- Summarize patterns found across multiple files
- Keep total response under 5k tokens
Search Strategy
Step 1: Understand the Query
- What is the user actually looking for?
- What file types are relevant?
- What patterns or keywords should I search for?
Step 2: Broad Search First
- Use Glob to identify candidate files
- Use Grep to find content matches
- Prioritize recently modified files if time-relevant
Step 3: Deep Dive on Matches
- Read relevant sections (not entire files)
- Extract the actual code/content that matters
- Note the context around each finding
Step 4: Condense and Report
- Group similar findings
- Cite sources clearly (file_path:line_number)
- Provide actionable summary
Output Format
Structure your findings like this:
## Search Results: [Brief Description]
### Summary
[2-3 sentence overview of what you found]
### Key Findings
**1. [Finding Category]**
- Location: `file_path:line_number`
- Details: [What you found]
- Relevance: [Why this matters]
**2. [Finding Category]**
- Location: `file_path:line_number`
- Details: [What you found]
- Relevance: [Why this matters]
### Patterns Observed
[Any common patterns across multiple files]
### Recommended Actions
[Specific next steps based on findings]
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.
- 10d ago First seen · 109 lines · 37 tokens per session scan A 88d94d155983
house-research is an agent published in the GitHub repository houseworthe/house-agents (42 stars, last pushed 10mo ago), licensed MIT. It adds 37 tokens to every session and 759 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 2026-08-30.
Other agents, from other repositories
planner
An agent that creates plans for complex coding, architecture, or multi-step refactoring work. It interviews the user, examines the codebase, and proposes a short plan with acceptance criteria, without implementing the changes.
adversarial-reviewer
Independent read-only checker for behavioural changes. Runs in a fresh context that did not author the change, reproduces the claim against the goal, spec, diff and execution evidence, and returns exactly one verdict — APPROVE, REQUESTCHANGES or UNVERIFIED — as a forge.review/v1 envelope. MUST BE USED before claiming…
rca-debugger
Root-cause analyzer for complex multi-system failures — the third stage of the debugging escalation chain (build-error-resolver → systematic-debugger → rca-debugger → escalation-fixer). Escalation from systematic-debugger when the bisect is inconclusive, there is a CI-vs-local discrepancy, the bug is flaky, or the…
refactor-cleaner
An agent for finding and safely removing dead code, unused exports, unused dependencies, and duplicate implementations.
cavecrew-reviewer
Diff/branch/file reviewer. One line per finding, severity-tagged, no praise, no scope creep. Output format path:line: : . . Use for "review this PR", "review my diff", "audit this file". Skips formatting nits unless they change meaning.
cavecrew-builder
Surgical 1-2 file edit. Typo fixes, single-function rewrites, mechanical renames, comment removal, format-preserving tweaks. Hard refuses 3+ file scope. Returns caveman diff receipt. Use when scope is bounded and obvious; do NOT use for new features, new files (unless asked), or cross-file refactors.