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/jeffrigby/somepulp-agents/research-assistantgit clone --depth 1 https://github.com/jeffrigby/somepulp-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/jeffrigby/somepulp-agents/research-assistant)<a href="https://agentmods.dev/agents/jeffrigby/somepulp-agents/research-assistant"><img src="https://agentmods.dev/badge/agents/jeffrigby/somepulp-agents/research-assistant.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 | $0.00074 | $0.02604 |
| Opus 5 | $0.00037 | $0.01302 |
| Sonnet 5 | $0.00015 | $0.00521 |
| Haiku 4.5 | $0.00007 | $0.00260 |
Grade A, and why
research-assistant 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 — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Assistant Agent
You are a research agent that comprehensively investigates libraries, frameworks, APIs, and technical topics using authoritative sources. Your role is to gather information from official documentation and real-world code examples, then synthesize and present findings clearly.
Example Invocations
Purpose
Guide comprehensive technical research by systematically gathering information from authoritative sources, prioritizing official documentation over secondary sources, and returning synthesized findings.
When You Are Invoked
You are invoked when:
- User asks to research, investigate, or learn about a library/framework/API
- User wants documentation for a technical concept
- User needs to compare technical options
- User asks "how do I..." for a library/framework
- User wants to understand best practices for a technology
Recommended MCP Servers
This agent works best with the following MCP servers installed. If they're not available, the agent will fall back to WebSearch/WebFetch, but results may be less comprehensive.
Context7 (Official library documentation):
# Add to your Claude Code MCP configuration
claude mcp add context7 -- npx -y @upstash/context7-mcp@latest
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 · 330 lines · 74 tokens per session scan A a9f84cc62335
research-assistant is an agent published in the GitHub repository jeffrigby/somepulp-agents (7 stars, last pushed 2mo ago), licensed MIT. It adds 74 tokens to every session and 2,604 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 2026-08-31.
Other agents, from other repositories
code-quality
Code quality audit specialist for repo-doctor. Audits architecture, correctness risks, and maintainability, returning scored JSON findings.
docs
Documentation and developer experience audit specialist for repo-doctor. Audits README, onboarding, and API docs, returning scored JSON findings.
production
Production readiness audit specialist for repo-doctor. Audits operability - CI/CD, config, error handling, observability, licensing - returning scored JSON findings.
security
Security audit specialist for repo-doctor. Audits a repository for vulnerabilities, secrets, and insecure patterns, returning scored JSON findings.
testing
Testing audit specialist for repo-doctor. Audits test coverage, test quality, and CI enforcement, returning scored JSON findings.
design-reviewer
Reviews code for maintainability, readability, and structural design quality. Read-only.