talos-mcp-server: Agent for Claude Code

.claude/agents/researcher.md

researcher is an agent for Claude Code from Nosmoht/talos-mcp-server. It costs 25 tokens per session (610 once invoked), scanned A, original, MIT.

A read-only research agent that investigates uncertain implementation or review questions using the repository first and official documentation when needed.

In plain words
What is it for?
Use it to check API behavior, project conventions, or earlier decisions and receive findings with file or documentation sources and a stated confidence level.
Why use it?
It reduces guesswork by requiring evidence and citations, while leaving code changes to someone else.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is Nosmoht/talos-mcp-server's own configuration. It tells Claude Code how to work on talos-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything talos-mcp-server configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/Nosmoht/talos-mcp-server/main/.claude/agents/researcher.md
Clone the repo
git clone --depth 1 https://github.com/Nosmoht/talos-mcp-server

Made for: Claude Code.

Wrote 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.

agentmods badge for researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/nosmoht/talos-mcp-server/researcher/github.svg)](https://agentmods.dev/agents/nosmoht/talos-mcp-server/researcher)
Your own site
<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.

agentmods 80×15 button for researcher

Your own site · 80×15
<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>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 610 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 9d ago against content hash 0e0cc68cad15, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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.

.claude/agents/researcher.md · 55 lines

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

  1. 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.
  2. Official docs fallback: If local sources are insufficient, search official documentation — Go standard library, Talos Linux docs, MCP SDK docs, COSI runtime docs.
  3. Always cite: Every finding must include the source (file:line for repo, URL for external docs).
  4. State confidence: Distinguish between what you found and what you're inferring.
  5. Nothing found: If no grounding found after repo + official docs, emit Confidence: none and list what was searched. Do not speculate. When Confidence is none, 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>

Read the full file on GitHub · 55 lines

Changes

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.

  1. 9d ago First seen · 55 lines · 25 tokens per session scan A 0e0cc68cad15

Subscribe to this mod's changes

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.