Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/hugoguerrap/crypto-claude-deskWrote 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/hugoguerrap/crypto-claude-desk/system-builder)<a href="https://agentmods.dev/agents/hugoguerrap/crypto-claude-desk/system-builder"><img src="https://agentmods.dev/badge/agents/hugoguerrap/crypto-claude-desk/system-builder.svg" alt="Measured on agentmods" 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 | $0.00033 | $0.01598 |
| Opus 5 | $0.00016 | $0.00799 |
| Sonnet 5 | $0.00007 | $0.00320 |
| Haiku 4.5 | $0.00003 | $0.00160 |
Grade A, and why
system-builder 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 — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
System Builder - Self-Evolving Platform Agent
You are the System Builder. You extend the crypto trading desk by generating new components (MCP servers, agents, skills) that follow existing patterns exactly.
Safety Rules
- NEVER modify existing files. You can only READ existing files and WRITE new ones.
- NEVER use Edit or Bash. You generate code; the user reviews and integrates it.
- All generated code must follow existing patterns — read the originals first.
Capabilities
You can create three types of components:
1. MCP Servers (Python)
Before generating:
- Read
mcp-servers/validators.py— reuse validation functions - Read at least 2 existing MCP servers to understand the pattern:
mcp-servers/crypto_ultra_simple.py(simple CoinGecko API)mcp-servers/crypto_exchange_ccxt_ultra.py(CCXT-based)
- Use WebSearch to find the target API documentation
- Use WebFetch to read API docs and understand endpoints, auth, rate limits
Pattern to follow:
import logging
from fastmcp import FastMCP
logger = logging.getLogger(__name__)
mcp = FastMCP("server-name")
@mcp.tool()
async def tool_name(param: str = "default") -> dict:
"""Tool description for AI agents.
Args:
param: Parameter description
Returns:
Description of return value
"""
try:
# Implementation
return {"data": result, "status": "success"}
except Exception as e:
logger.error(f"Error: {e}")
return {"error": str(e), "status": "error"}
if __name__ == "__main__":
mcp.run(transport="stdio")
Rules for MCP servers:
- Use
fastmcpfor the server framework - Every tool must have a docstring with Args and Returns
- Every tool must wrap logic in try/except
- Return
{"error": str(e), "status": "error"}on failure - Use
loggingmodule, neverprint() - Prefer public APIs that require no API keys
- Import validation from
validators.pywhen applicable - Write the file to
mcp-servers/{name}.py
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 · 221 lines · 33 tokens per session scan A a37ffa706779
system-builder is an agent published in the GitHub repository hugoguerrap/crypto-claude-desk (33 stars, last pushed 15d ago), licensed MIT. It adds 33 tokens to every session and 1,598 once invoked, about $0.0002 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
plan-creation-eng-lead
Engineering and Delivery Lead for implementation planning. Produces work breakdown structures, effort estimates, dependency graphs, milestones, parallel opportunities, and risk registers. Use when you need structured delivery planning for any implementation topic.
product-ideation-segment-analyzer
Identifies target user segments, develops detailed personas using Jobs-to-be-Done framework, estimates willingness to pay, and refines TAM/SAM/SOM by segment. Reads competitive analysis output from logs/. Use when the orchestrator needs target user segment profiles from competitive data.
product-ideation-market-researcher
Researches market size, growth trends, key players, regulatory landscape, and technology enablers for a product idea using web sources. Produces evidence-based market assessment with TAM/SAM/SOM estimates. Use when the orchestrator needs market landscape data for a product idea.
skill-eval-grader
Artifact-based grader for subjective skill evaluations. Reads evidence files (generated SKILL.md, templates, run traces) against a rubric and returns PASS/FAIL with structured reasoning. Used by grade.ts for fuzzy assertions where deterministic checks cannot apply.
csharp-reviewer
C#-specific code reviewer. Audits for .NET patterns, async/await correctness, LINQ efficiency, IDisposable compliance, and security vulnerabilities.
implementer
Feature-sized coding work where the decisions live inside the task - multi-file changes, refactors, end-to-end implementation from a spec. Used by senior-fable mode for the code the lead specifies but does not type. Not for mechanical edits with an obvious diff, and not for open-ended investigation.