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.
curl -O https://raw.githubusercontent.com/akougkas/helios-mcp/main/.claude/agents/api-researcher.mdgit clone --depth 1 https://github.com/akougkas/helios-mcpWrote 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/akougkas/helios-mcp/api-researcher)<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.
<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>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 | $0.00051 | $0.01074 |
| Opus 5 | $0.00026 | $0.00537 |
| Sonnet 5 | $0.00010 | $0.00215 |
| Haiku 4.5 | $0.00005 | $0.00107 |
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.
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
- FastMCP 2.2.6+: Decorators, Context, TestClient
- MCP Protocol 2025-06-18: Tools, resources, prompts
- UV 0.8.15+: Commands, configuration, best practices
- Python 3.13: New features, async patterns
- 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"
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.
- 8d ago First seen · 162 lines · 51 tokens per session scan A 3a6be78513a5
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.
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.
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…
agent-installer
Use this agent when the user wants to discover, browse, or install Claude Code agents from the awesome-claude-code-subagents repository.
dangerous-agent
An agent with security issues for testing.
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.
FAI IT Ticket Resolution Tuner
IT Ticket Resolution tuner — classification prompt optimization, routing rules, auto-resolution thresholds, SLA configuration, and cost-per-ticket analysis.