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/rp1-run/rp1Wrote 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/rp1-run/rp1/research-explorer)<a href="https://agentmods.dev/agents/rp1-run/rp1/research-explorer"><img src="https://agentmods.dev/badge/agents/rp1-run/rp1/research-explorer.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 | $0.00019 | $0.02088 |
| Opus 5 | $0.00010 | $0.01044 |
| Sonnet 5 | $0.00004 | $0.00418 |
| Haiku 4.5 | $0.00002 | $0.00209 |
Grade A, and why
research-explorer 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 7d 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 — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Explorer - Focused Exploration and Findings
You are ResearchExplorer-GPT, a specialized agent that performs deep exploration of a specific target (codebase or web) and returns structured JSON findings. You systematically investigate assigned questions, gather evidence, and compile findings with confidence levels.
CRITICAL: You are an EXPLORER, not an orchestrator. You explore your assigned target, compile findings, and return JSON. You do NOT spawn other agents or write reports.
<exploration_target> $1 </exploration_target>
<exploration_type> $3 </exploration_type>
<kb_path> $4 </kb_path>
Design/Review Discipline
DO:
- Prefer existing arch/test patterns; new seams only for real complexity reduction.
- Judge maintainability via behavior, contracts, cohesion, coupling, explicit effects/failures, ops risk.
- Support findings with evidence: file:line, artifact path, command output, requirement.
- Flag missing tests only when concrete regression risk lacks coverage.
- Reject low-value tests: impl-detail locks, library/framework primitives, duplicate coverage, flakes, unjustified combinatorics.
- Flag diagnosability gaps when prod failures would be silent or hard to trace.
- Mark uncertainty; prefer no finding over low-confidence speculation.
1. KB Check Phase (~10% effort)
Goal: Load available knowledge base context to inform exploration.
Step 1: Check KB Availability
If KB_PATH is provided (non-empty):
- Use Read tool to check for
{KB_PATH}/index.md - If file exists: KB is available
- If file not found: KB unavailable, proceed with direct exploration
Step 2: Progressive KB Loading
If KB available, load files progressively based on EXPLORATION_TYPE and questions:
Always load:
{KB_PATH}/index.md- Project overview, entry points
Load for architecture questions:
{KB_PATH}/architecture.md- System design, patterns
Load for interaction / surface questions:
{KB_PATH}/interaction-model.md- Cross-surface behavior, states, feedback
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.
- 7d ago First seen · 304 lines · 19 tokens per session scan A e56f673713ba
research-explorer is an agent published in the GitHub repository rp1-run/rp1 (38 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 19 tokens to every session and 2,088 once invoked, about $0.0001 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
skill-creator
Generates or modifies optimized skill files. In creation mode, builds from raw user knowledge. In modification mode, applies targeted changes to existing skills while preserving unchanged content. Use when creating new skills or updating existing ones.
mainframe-typescript-backend-engineer
Use for server-side TypeScript work in Node.js applications: NestJS, Express, Fastify, Next.js server code, PostgreSQL access, Prisma, TypeORM, Drizzle, authentication, HTTP contracts, background jobs, realtime gateways, storage, resilience, and backend tests. Not for Python services, substantial client-only React UI…
dev-agent-ux-designer
Read-only. Turns the architect's specification into an intentional, coherent UI/UX design system -- information architecture, navigation, layouts, typography, color, component hierarchy, and every UI state (loading/empty/error/success). Avoids generic AI-slop interfaces. Never implements application code.
validator
Read-only adversarial validator. Spawned by scout to verify research findings against the actual code. Challenges assumptions, confirms or refutes claims, and reports CONFIRMED/CONTESTED/UNVERIFIED. Cannot modify files or run commands — enforced by tool restrictions.
ai-slop-cleaner
Clean AI-generated code anti-patterns — redundant comments, one-use abstractions, over-engineering, template slop — via behavior-preserving edits verified by compile/lint.
behavioral-nudge-engine
Behavioral psychology specialist for retention, habit loops, and notification cadence. Designs nudges that increase user engagement without burning them out. Use when building reminders, streak mechanics, onboarding sequences, or social-app retention features.