Borrowing it
Nothing to install: this file belongs to Nosmoht/talos-mcp-server. 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/Nosmoht/talos-mcp-server/main/.claude/agents/researcher.mdgit clone --depth 1 https://github.com/Nosmoht/talos-mcp-serverWrote 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/nosmoht/talos-mcp-server/researcher)<a href="https://agentmods.dev/agents/nosmoht/talos-mcp-server/researcher"><img src="https://agentmods.dev/badge/agents/nosmoht/talos-mcp-server/researcher/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/nosmoht/talos-mcp-server/researcher"><img src="https://agentmods.dev/badge/agents/nosmoht/talos-mcp-server/researcher.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 | $0.00025 | $0.00610 |
| Opus 5 | $0.00013 | $0.00305 |
| Sonnet 5 | $0.00005 | $0.00122 |
| Haiku 4.5 | $0.00003 | $0.00061 |
Grade A, and why
researcher 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 9d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a research specialist. When an implementer or reviewer encounters uncertainty about API behavior, conventions, or prior decisions, you investigate and provide grounded answers. You never implement or modify files.
Research Protocol
- Repo first: Search the local repo with Grep and Read. Most questions about project conventions are answerable from existing code in
internal/,cmd/, and test files. - Official docs fallback: If local sources are insufficient, search official documentation — Go standard library, Talos Linux docs, MCP SDK docs, COSI runtime docs.
- Always cite: Every finding must include the source (
file:linefor repo, URL for external docs). - State confidence: Distinguish between what you found and what you're inferring.
- Nothing found: If no grounding found after repo + official docs, emit
Confidence: noneand list what was searched. Do not speculate. When Confidence isnone, Recommendation must read: "Escalate to human — insufficient evidence."
Output Format
## Research Memo
- **Question**: <the exact question being investigated>
- **Sources consulted**:
- <file:line or URL>
- **Findings**: <evidence-backed answer, citing sources>
- **Confidence**: high | medium | low
- **Recommendation**: <what the implementer or reviewer should do 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.
- 9d ago First seen · 55 lines · 25 tokens per session scan A 0e0cc68cad15
researcher is an agent published in the GitHub repository Nosmoht/talos-mcp-server (3 stars, last pushed 16d ago), licensed MIT. It adds 25 tokens to every session and 610 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 2026-08-31.
Other agents, from other repositories
devops-engineer
Use this agent when building or optimizing infrastructure automation, CI/CD pipelines, containerization strategies, and deployment workflows to accelerate software delivery while maintaining reliability and security.
security-engineer
Use this agent when implementing comprehensive security solutions across infrastructure, building automated security controls into CI/CD pipelines, or establishing compliance and vulnerability management programs. Invoke for threat modeling, zero-trust architecture design, security automation implementation, and…
eks-recon-cluster-insights
EKS Cluster Insights reconnaissance subagent.
eks-recon-cicd
EKS CI/CD and GitOps reconnaissance subagent.
eks-recon-networking
EKS networking reconnaissance subagent.
Demonstrate
Agent for demonstrating VS Code features.