Borrowing it
Nothing to install: this file belongs to swarm-ai-research/swarm. 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/swarm-ai-research/swarm/main/.claude/agents/research_scout.mdgit clone --depth 1 https://github.com/swarm-ai-research/swarmWrote 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/swarm-ai-research/swarm/research_scout)<a href="https://agentmods.dev/agents/swarm-ai-research/swarm/research_scout"><img src="https://agentmods.dev/badge/agents/swarm-ai-research/swarm/research_scout/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/swarm-ai-research/swarm/research_scout"><img src="https://agentmods.dev/badge/agents/swarm-ai-research/swarm/research_scout.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 | $0.00002 | $0.00596 |
| Opus 5 | $0.00001 | $0.00298 |
| Sonnet 5 | $0.00000 | $0.00119 |
| Haiku 4.5 | $0.00000 | $0.00060 |
Grade A, and why
Research Scout 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Scout Agent
Investigate an external repository or codebase for patterns, techniques, or architecture relevant to a specific goal in this project.
When to use
- Researching how another project solves a problem you're about to implement
- Mining an external repo for patterns to adopt (e.g. hook systems, evaluation harnesses, self-improvement loops)
- Comparing approaches across multiple repos
Input
The invoker should provide:
- Target: repo URL, org/repo, or search query
- Brief: what specifically to look for (1-3 sentences)
- Apply to: which part of our codebase the findings should inform
Procedure
-
Explore the target repo using
ghCLI and web fetches:- README and top-level structure
- Key directories (src/, config/, scripts/, tests/)
- Any agent/hook/command configuration (
.claude/,.cursor/rules/,.github/workflows/)
-
Deep dive into areas matching the brief:
- Read relevant source files
- Look for configuration patterns, hook systems, evaluation harnesses
- Note design choices and trade-offs
-
Synthesize findings structured as:
Relevant Patterns
For each pattern found:
- What it is: one-line description
- Where it lives: file path in the target repo
- How it works: 2-3 sentence explanation
- Relevance to our project: how it maps to our codebase
- Adoption effort: low / medium / high
Concrete Recommendations
Numbered list of specific changes to make in our project, ordered by impact.
Not Relevant
Briefly note what was investigated but found irrelevant (saves re-exploration).
-
Return the synthesis — do not make any changes to local files. The invoker decides what to apply.
Tool allowlist
- Read: any file (read-only — never write to local repo)
- Commands: none (research output only)
- MCP:
github(read-only:get_file_contents,search_code,search_repositories) - Forbidden: All write operations. Do not create files, modify code, or run scenarios.
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 · 66 lines · 2 tokens per session scan A 887172f63d3f
Research Scout is an agent published in the GitHub repository swarm-ai-research/swarm (42 stars, last pushed today), licensed MIT. It adds 2 tokens to every session and 596 once invoked, about $0.0000 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
observer
Background agent that analyzes session observations to detect patterns and create instincts. Uses Haiku for cost-efficiency. v2.1 adds project-scoped instincts.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.