backend-agent

backend-agent is an agent for Claude Code from Myst4ke/mcp-to-skills-converter. It costs 19 tokens per session (703 once invoked), scanned A, original, MIT.

A specialized coding agent for building the backend of MCP Finder, a tool for finding Model Context Protocol servers and tools.

In plain words
What is it for?
Use it to search npm and GitHub, scan local MCP servers, combine and cache results, validate input, and build the command-line search flow.
Why use it?
It brings together the planned search, caching, validation, command-line, and error-handling work needed by that backend.

Agent for Claude Code

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

Part of the spec-implementer-generated plugin — 3 skills, 4 agents shipped together

Good fit Use it to search npm and GitHub, scan local MCP servers, combine and cache results, validate input, and build the command-line search flow.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/myst4ke/mcp-to-skills-converter/backend-agent
Install

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.

Clone the repo
git clone --depth 1 https://github.com/Myst4ke/mcp-to-skills-converter

Made for: Claude Code.

Or install spec-implementer-generated, the plugin that ships this one along with the rest of its 3 skills, 4 agents.

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 backend-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/myst4ke/mcp-to-skills-converter/backend-agent/github.svg)](https://agentmods.dev/agents/myst4ke/mcp-to-skills-converter/backend-agent)
Your own site
<a href="https://agentmods.dev/agents/myst4ke/mcp-to-skills-converter/backend-agent"><img src="https://agentmods.dev/badge/agents/myst4ke/mcp-to-skills-converter/backend-agent/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 backend-agent

Your own site · 80×15
<a href="https://agentmods.dev/agents/myst4ke/mcp-to-skills-converter/backend-agent"><img src="https://agentmods.dev/badge/agents/myst4ke/mcp-to-skills-converter/backend-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 703 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 $0.00019 $0.00703
Opus 5 $0.00010 $0.00351
Sonnet 5 $0.00004 $0.00141
Haiku 4.5 $0.00002 $0.00070

Measured 11d ago against content hash f1304443139e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

backend-agent 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 11d 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/spec-implementer-generated/agents/backend-agent.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Backend Implementation Agent (US-1)

Purpose

Implements backend tasks (TASK-1.1 through TASK-1.11) for MCP Finder including data models, fuzzy search, API services, CLI components, and error handling.

Technologies: TypeScript, Node.js, fuse.js, axios, chalk, inquirer

Key Skills to Use

  • api-development: For TASK-1.2-1.6 (search services and aggregation)
  • component-development: For TASK-1.8-1.9 (CLI components)
  • security-implementation: For TASK-1.10 (input validation)
  • configuration: For TASK-1.1, TASK-1.7 (data model, caching)

Workflow

  1. Use capability skills when available
  2. Implement with TypeScript strict mode
  3. Run tests after implementation
  4. Update state and commit

Assigned Tasks

  • TASK-1.1: Define MCPSearchResult data model
  • TASK-1.2: Implement fuzzy search with fuse.js
  • TASK-1.3: Create npm registry search service
  • TASK-1.4: Create GitHub API search service
  • TASK-1.5: Implement local MCP scanner
  • TASK-1.6: Create search result aggregator
  • TASK-1.7: Implement search result caching
  • TASK-1.8: Create CLI interface for search
  • TASK-1.9: Implement user selection flow
  • TASK-1.10: Add input validation and sanitization
  • TASK-1.11: Implement error handling and fallbacks

Implementation Guidelines

For Each Task

  1. Read task details from specs/mcp-to-skills-converter/US-1/tasks.md
  2. Check dependencies are completed
  3. Invoke appropriate capability skill
  4. Implement following skill guidance
  5. Run relevant tests
  6. Update .impl-state.json
  7. Create atomic git commit
  8. Report completion

Task-Specific Notes

TASK-1.1: Foundation data model

  • Create src/types/mcp-search.ts
  • Define MCPSearchResult interface
  • Add supporting types (MCPSource, MCPMetadata)
  • Include type guards and JSDoc

TASK-1.2-1.5: API Services (can be parallel after 1.1)

  • Use api-development skill for each
  • Implement with retry logic and timeout handling
  • Parse responses to MCPSearchResult format
  • Handle errors gracefully

TASK-1.6: Core integration

  • Combine all API services
  • Use Promise.allSettled for parallel execution
  • Implement deduplication
  • Apply fuzzy matching to results

Read the full file on GitHub · 87 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. 11d ago First seen · 87 lines · 19 tokens per session scan A f1304443139e

Subscribe to this mod's changes

backend-agent is an agent published in the GitHub repository Myst4ke/mcp-to-skills-converter (1 stars, last pushed 10mo ago), licensed MIT. It adds 19 tokens to every session and 703 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.

Related

Other agents, from other repositories

skilltracer

Evaluates completed work against existing skills, creates new skills or updates existing ones. Spawned by Claude main after every task.

Lover0ne/devstuff · 29 tokens

skill-writer

Writes a single utility skill based on project analysis. Spawned as part of a swarm.

Lover0ne/devstuff · 22 tokens

call-tracer

Orchestrates parallel call tree tracing using subagents for each entry point category (Controllers, LiveViews, Workers, GenServers). Use proactively when debugging unexpected values, tracing request flow, or planning signature changes.

oliver-kriska/claude-elixir-phoenix · 46 tokens

go-expert

Go concurrency, error handling, stdlib patterns, Chi/Echo web frameworks specialist. Use when writing Go code, designing concurrent systems, or building Go web services. Trigger phrases: Go, Golang, goroutine, channel, Chi, Echo, stdlib, context, error handling, interface, module, go test.

travisjneuman/.claude · 69 tokens

api-integration-specialist

Third-party API integration, webhook handling, OAuth flows, rate limiting, and SDK wrapping specialist. Use when integrating external APIs, building webhook handlers, or creating API client libraries. Trigger phrases: API integration, webhook, third-party API, SDK wrapper, OAuth flow, rate limiting, retry strategy…

travisjneuman/.claude · 74 tokens

serverless-specialist

AWS Lambda, Cloudflare Workers, Vercel Edge Functions, and serverless architecture specialist. Use when building serverless functions, optimizing cold starts, or designing event-driven serverless systems. Trigger phrases: serverless, Lambda, Edge Functions, Workers, Vercel, Cloudflare Workers, cold start, function as…

travisjneuman/.claude · 72 tokens