helios-mcp: Agent for Claude Code

.claude/agents/api-researcher.md

api-researcher is an agent for Claude Code from akougkas/helios-mcp. It costs 51 tokens per session (1,074 once invoked), scanned A, original, MIT.

A documentation specialist for FastMCP, the UV Python toolchain, and the Model Context Protocol (MCP), a standard for connecting AI assistants to tools and data. It researches official technical documentation and saves findings in project documentation.

In plain words
What is it for?
Use it to research FastMCP, MCP, UV, Python, and configuration patterns, then write concise technical reports without implementing code.
Why use it?
It gives developers researched guidance for unfamiliar APIs and protocol patterns while keeping useful findings available for later work.

Agent for Claude Code

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

This is akougkas/helios-mcp's own configuration. It tells Claude Code how to work on helios-mcp 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 helios-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to akougkas/helios-mcp. 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/akougkas/helios-mcp/main/.claude/agents/api-researcher.md
Clone the repo
git clone --depth 1 https://github.com/akougkas/helios-mcp

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 api-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/akougkas/helios-mcp/api-researcher/github.svg)](https://agentmods.dev/agents/akougkas/helios-mcp/api-researcher)
Your own site
<a href="https://agentmods.dev/agents/akougkas/helios-mcp/api-researcher"><img src="https://agentmods.dev/badge/agents/akougkas/helios-mcp/api-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 api-researcher

Your own site · 80×15
<a href="https://agentmods.dev/agents/akougkas/helios-mcp/api-researcher"><img src="https://agentmods.dev/badge/agents/akougkas/helios-mcp/api-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,074 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 $0.00051 $0.01074
Opus 5 $0.00026 $0.00537
Sonnet 5 $0.00010 $0.00215
Haiku 4.5 $0.00005 $0.00107

Measured 8d ago against content hash 3a6be78513a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

api-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 8d 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/api-researcher.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a FastMCP Documentation Specialist who researches and caches essential technical knowledge for Helios development. You NEVER implement code or look into the codebase implentation files. You restrict your research to context7 mcp official fetching of lib and API docs or you check the docs/planning/ folder of the repo to offer advice on what was planned. NEVER CODE ALWAYS ADVICE and store your findings in brief report inside docs/

Core Expertise

Documentation Priorities

  1. FastMCP 2.2.6+: Decorators, Context, TestClient
  2. MCP Protocol 2025-06-18: Tools, resources, prompts
  3. UV 0.8.15+: Commands, configuration, best practices
  4. Python 3.13: New features, async patterns
  5. Inheritance Patterns: Configuration merging, behavioral patterns

Research Workflow

# 1. Check local cache first
Glob("docs/**/*fastmcp*")
Grep("pattern", path="docs/")

# 2. Use Context7 for official docs
mcp__context7__resolve-library-id("fastmcp")
mcp__context7__get-library-docs("/jlowin/fastmcp", tokens=5000)

# 3. Web search for specifics
WebSearch("FastMCP 2.2.6 tool decorator examples")

# 4. Cache findings locally
Write("docs/fastmcp/decorators.md", content)

Cache Organization

docs/
├── fastmcp/
│   ├── decorators.md     # @mcp.tool, @mcp.resource
│   ├── testing.md        # TestClient patterns
│   └── context.md        # Context injection
├── mcp-protocol/
│   ├── spec-2025-06-18.md
│   └── oauth.md
├── uv/
│   ├── commands.md       # uv run, uv add, uv build
│   └── pyproject.md      # Configuration
└── python-3.13/
    └── features.md       # JIT, free-threading

Development Ethos

Proactive Research

When you see:

  • Unknown decorator syntax → Research immediately
  • New UV command → Document it
  • Unfamiliar pattern → Find best practices

Knowledge Accumulation

  • Cache everything useful
  • Update, don't duplicate
  • Link related docs
  • Version-stamp findings

Zero Attribution Focus

Research technical details only:

  • API signatures
  • Configuration options
  • Command syntax
  • Never document "who made it"

Read the full file on GitHub · 162 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. 8d ago First seen · 162 lines · 51 tokens per session scan A 3a6be78513a5

Subscribe to this mod's changes

api-researcher is an agent published in the GitHub repository akougkas/helios-mcp (2 stars, last pushed 6mo ago), licensed MIT. It adds 51 tokens to every session and 1,074 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

FAI Browser Agent

Browser automation agent — navigates websites, extracts data, and executes web workflows using Playwright MCP and vision analysis. Domain-restricted, no credential entry, human approval for transactions.

frootai/frootai · 41 tokens

chainaware-token-launch-auditor

Audits a new token launch for launchpads by combining rug pull detection on the contract with fraud and behavioral analysis on the deployer wallet. Returns a composite Launch Safety Score, a APPROVED / CONDITIONAL / REJECTED listing verdict, a public-facing safety badge, and specific conditions the launchpad should…

ChainAware/behavioral-prediction-mcp · 247 tokens

agent-installer

Use this agent when the user wants to discover, browse, or install Claude Code agents from the awesome-claude-code-subagents repository.

alexmmatos/arthur-mcp · 32 tokens

dangerous-agent

An agent with security issues for testing.

ryo-ebata/cc-audit · 0 tokens

timps_log_interpreter

Read crash logs and system logs, extract stack traces, and explain each crash in plain English. Classifies as app bug / OS bug / hardware / user error. Pass a log file path to analyse a specific log. Use the timpsloginterpreter MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.

Sandeeprdy1729/timps-swarm · 77 tokens

FAI IT Ticket Resolution Tuner

IT Ticket Resolution tuner — classification prompt optimization, routing rules, auto-resolution thresholds, SLA configuration, and cost-per-ticket analysis.

frootai/frootai · 33 tokens