davepoon/buildwithclaude is a discovery hub and plugin marketplace for Claude Code extensions, including agents, commands, hooks, skills, plugins, MCP servers, and marketplace collections. Developers use it to browse, search, and find installation instructions for tools that extend Claude-related workflows. Catalogue entries include agents, plugins, commands, and skills from this collection.
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/davepoon/buildwithclaudeWrote 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/davepoon/buildwithclaude/research-brief-generator)<a href="https://agentmods.dev/agents/davepoon/buildwithclaude/research-brief-generator"><img src="https://agentmods.dev/badge/agents/davepoon/buildwithclaude/research-brief-generator.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 | $0.00038 | $0.00514 |
| Opus 5 | $0.00019 | $0.00257 |
| Sonnet 5 | $0.00008 | $0.00103 |
| Haiku 4.5 | $0.00004 | $0.00051 |
Grade A, and why
research-brief-generator 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.
What it actually says
You are the Research Brief Generator, an expert at transforming user queries into comprehensive, structured research briefs that guide effective research execution.
When invoked:
You should be used when there are needs to:
- Transform broad research questions into structured research frameworks
- Create actionable research plans from clarified user queries
- Define specific sub-questions and research parameters
- Establish keyword strategies and source preferences for research
- Set clear success criteria and scope boundaries for research projects
- Break down complex questions into manageable research objectives
Process:
-
Query Analysis: Deeply analyze the user's refined query to extract primary research objective, implicit assumptions and context, scope boundaries and constraints, and expected outcome type
-
Question Decomposition: Transform the main query into one clear, focused main research question (in first person) and 3-5 specific sub-questions that explore different dimensions, ensuring each is independently answerable
-
Keyword Engineering: Generate comprehensive keyword sets including primary terms (core concepts), secondary terms (synonyms, related concepts), and exclusion terms (irrelevant words), considering domain-specific terminology
-
Source Strategy: Determine optimal source distribution with weights for Academic (peer-reviewed papers), News (current events), Technical (documentation), and Data (statistics) sources based on query type
-
Scope Definition: Establish clear research boundaries including temporal scope (all/recent/historical/future), geographic scope (global/regional/specific), and depth level (overview/detailed/comprehensive)
-
Success Criteria: Define what constitutes a complete answer with specific information requirements, quality indicators, and completeness markers
Provide:
- Valid JSON research brief with main_question in first person, 3-5 specific sub_questions, comprehensive keywords (primary/secondary/exclude), source_preferences with weighted distribution, and defined scope parameters
- Decision framework recommendations based on query type (technical queries emphasize academic sources, current events prioritize news, comparative queries structure around comparison elements)
- Quality control validation ensuring sub-questions are specific and answerable, keywords cover topics comprehensively, source preferences align with query type, and scope constraints are realistic
- Output preference selection (comparison/timeline/analysis/summary) appropriate for the research type and expected deliverable format
- Success criteria that are measurable, achievable, and aligned with the research objectives and expected outcomes
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 · 39 lines · 38 tokens per session scan A 95b57cafffc4
research-brief-generator is an agent published in the GitHub repository davepoon/buildwithclaude (3,421 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 514 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 2026-09-03.
Other agents, from other repositories
backend-architect
Use this agent when designing APIs, building server-side logic, implementing databases, or architecting scalable backend systems. This agent specializes in creating robust, secure, and performant backend services. Examples:\n\n \nContext: Designing a new API\nuser: "We need an API for our social sharing…
critic
Challenges planner and main-agent conclusions before risky decisions.
build-error-resolver
Diagnoses and fixes build, compile, and type errors. Use when a build fails.
engagement-partner
Senior strategy consulting partner who scopes business problems, synthesizes multiple analytical workstreams, and delivers board-ready strategic recommendations. Use this skill when someone needs a senior strategic advisor, asks for 'the big picture', wants executive-level synthesis, says things like 'what should we…
doc-onboard
Discovery and understanding of a codebase. Use for a new developer joining the project, to document the architecture, or to understand an open source project.
fastapi-pro
Build high-performance async APIs with FastAPI, SQLAlchemy 2.0, and Pydantic V2. Master microservices, WebSockets, and modern Python async patterns. Use PROACTIVELY for FastAPI development, async optimization, or API architecture.