Agent skill

Gentech Blockrun

by BlockRunAI in BlockRunAI/blockrun-mcp

GenTech Labs' integration patterns for BlockRun MCP from Hermes Agent.

MITAuto-check passedBackend & APIs

Install Gentech Blockrun

skills CLI
$ npx skills add BlockRunAI/blockrun-mcp --skill gentech-blockrun -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install BlockRunAI/blockrun-mcp gentech-blockrun --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/BlockRunAI/blockrun-mcp.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/gentech-blockrun .claude/skills/gentech-blockrun && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
gentech-blockrun
GitHub stars
392
Token cost
~2.5k tokens
SKILL.md length
500 words
Files
1
Skills in repo
17
Repo updated
First seen
Licence
MIT

At a glance

GenTech Labs' integration patterns for BlockRun MCP from Hermes Agent.

  • Tasks that involve Third-party API integration
  • SKILL.md covers Getting Started, Daily Usage Patterns, Multi-Tool Pipelines and Cost Optimization Strategies, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Tasks that involve Crypto and DeFi analysis

What it does

Gentech Blockrun is an agent skill from BlockRunAI/blockrun-mcp. GenTech Labs' integration patterns for BlockRun MCP from Hermes Agent. Covers daily usage patterns, cost-optimized workflows, multi-tool pipelines, and reliable error handling for BlockRun's full toolset.

Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Backend & APIs, covering Third-party API integration and Crypto and DeFi analysis. It works with Model Context Protocol. The repository describes itself as: Live data for AI agents — search, research, markets, crypto, X/Twitter. Pay-per-call via x402 micropayments. The licence is MIT.

When your agent uses it

  • Tasks that involve Third-party API integration
  • Tasks that involve Crypto and DeFi analysis

Example prompts

  • “/gentech-blockrun”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit e9b2bd5. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are python, bash and yaml).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • blockrun.ai
    • t.me

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Gentech Blockrun loads about 2.5k tokens when it runs. Until then it costs about 55 tokens; SKILL.md has 500 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~55
When it runs · the whole SKILL.md, loaded when a task matches
~2.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from BlockRunAI/blockrun-mcp at commit e9b2bd5, republished under its MIT licence (© BlockRunAI). 500 words, ~2,536 tokens.

Download SKILL.mdSave it as .claude/skills/gentech-blockrun/SKILL.md (or your agent's skills folder).
name
gentech-blockrun
description
GenTech Labs' integration patterns for BlockRun MCP from Hermes Agent. Covers daily usage patterns, cost-optimized workflows, multi-tool pipelines, and reliable error handling for BlockRun's full toolset.
triggers
blockrun, blockrun chat, blockrun search, blockrun price, blockrun defi, blockrun video, blockrun music, blockrun speech, blockrun wallet, blockrun rpc…

GenTech Labs — BlockRun Integration Patterns

Real-world patterns from running BlockRun MCP in production across 32 cron jobs and daily agent operations.


Getting Started

Initial Wallet Setup
bash
# Set up BlockRun wallet (one-time)
blockrun_wallet(action="setup")
# → Follow the QR to fund the wallet with USDC
Budget Controls
python
# Set a global budget cap so spending never surprises you
blockrun_wallet(action="budget", budget_action="set", budget_amount=10.0)

# Spawn child agents with delegate budgets
blockrun_wallet(action="delegate", agent_id="researcher", agent_limit=2.0)
blockrun_wallet(action="delegate", agent_id="data-poller", agent_limit=0.50)
Check Balance
python
blockrun_wallet(action="status")
# → Two wallets: Base + Solana. Active chain shown. Check before expensive runs.

Daily Usage Patterns

Pattern 1: Regular Price Checks (FREE)

Crypto, FX and commodity quotes cost nothing — blockrun_price is free for those categories (stocks/usstock quotes are not served since 2026-09-05 — the gateway 501s before payment; only the ticker catalog works). Use them liberally. (blockrun_surf, which used to charge $0.0085 for the same quote, was removed in 0.49.0 — the gateway 410s every Surf path since 2026-09-06.)

python
# Single price
blockrun_price(action="price", category="crypto", symbol="BTC-USD")

# Batch of prices
blockrun_price(action="price", category="crypto", symbol="ETH-USD")
blockrun_price(action="price", category="crypto", symbol="SOL-USD")

# Free — discover available symbols
blockrun_price(action="list", category="crypto", query="sol")

Cost: $0 — crypto/FX/commodity price and list calls are both free. category:"stocks" price/history currently return 501 (equity quotes withdrawn 2026-09-05, nothing charged); its list catalog is free.

Pattern 2: Token Research Pipeline (~$0.018)

Start with the free tools, then pay only for what they cannot answer.

python
# 1. Free — DEX liquidity + volume (free endpoint)
blockrun_dex({ query: "SOL" })

# 2. FREE — CEX price (crypto category is free)
blockrun_price(action="price", category="crypto", symbol="SOL-USD")

# 3. $0.0060 each — Protocol TVL
blockrun_defi({ path: "protocols" })
blockrun_defi({ path: "protocol/jupiter" })

# 4. $0.0060 — Chain TVL
blockrun_defi({ path: "chains" })

Total: ~$0.018 per full token analysis (2 free calls + 3 x $0.0060 DefiLlama). Replace CoinGecko/CMC tabs entirely.

Pattern 3: Research + Synthesis (~$0.011 + chat)

Use Exa (neural search) + BlockRun Chat (second opinion) for thorough research.

python
# 1. $0.0110 — Neural web search with Exa
blockrun_exa({ path: "search", body: {
  query: "latest AI agent infrastructure developments 2026",
  numResults: 10,
  category: "research paper"
}})

# 2. per-token — Get second opinion from GLM-5 (excellent for technical details)
blockrun_chat({ mode: "glm", message: "Summarize the key trends..." })

Cost-conscious tip: Use mode: "free" on blockrun_chat for zero-cost generation (NVIDIA models).

Pattern 4: Agent-to-Agent Billing

Use blockrun_wallet + agent_id for multi-agent cost tracking.

python
# Allocate budget per agent group
blockrun_wallet(action="delegate", agent_id="research", agent_limit=2.0)
blockrun_wallet(action="delegate", agent_id="content", agent_limit=1.0)

# Pass agent_id on every call
blockrun_defi({ path: "protocols", agent_id: "research" })
blockrun_search({ body: { query: "latest news", sources: ["web"] }, agent_id: "research" })

# Audit at end of day
blockrun_wallet(action="report")

Multi-Tool Pipelines

DeFi Intelligence Pipeline
python
# 1. TVL & protocol health ($0.0060)
blockrun_defi({ path: "protocol/aave-v3" })

# 2. Yield pools ($0.0060)
blockrun_defi({ path: "yields" })

# 3. Token price (FREE — crypto category)
blockrun_price(action="price", category="crypto", symbol="AAVE-USD")

# 4. DEX activity (free)
blockrun_dex({ token: "0x7Fc66500c84A76Ad7e9c93437bFc5Ac33E2DDaE9" })
Portfolio Health Check
python
# 1. Current holdings (free — local data or blockrun_rpc)
blockrun_rpc({ network: "base", method: "eth_getBalance", params: ["0xabc...", "latest"] })

# 2. Token prices (FREE — crypto category)
blockrun_price(action="price", category="crypto", symbol="ETH-USD")
blockrun_price(action="price", category="crypto", symbol="USDC-USD")

# 3. Prediction market positions ($0.0085)
blockrun_markets({ path: "polymarket/positions" })
Content Generation Pipeline
python
# 1. Research ($0.0110)
blockrun_exa({ path: "search", body: { query: "agentic commerce trends", numResults: 5 }})

# 2. Image generation for post ($0.01675 cheapest to $0.106 quality)
blockrun_image({ prompt: "AI agent futuristic dashboard with neon grids" })

# 3. Voiceover for video ($0.0535/1k chars)
blockrun_speech({ input: "Your narration text here...", voice: "sarah" })

# 4. Music track ($0.1585)
blockrun_music({ prompt: "upbeat synthwave background" })

# 5. Short video clip ($0.421)
blockrun_video({ prompt: "animated data visualization", duration_seconds: 8 })

Cost Optimization Strategies

Tier Mapping
Call TypePriceFrequency
blockrun_price (list)FREEdaily discovery
blockrun_dexFREEunlimited
blockrun_rpc$0.0030on-chain reads (batch: $0.002/element + $0.001)
blockrun_wallet (status/report)FREEbefore every session
blockrun_price (quote)FREEcrypto/FX/commodity; stocks quotes not served (501 since 2026-09-05)
blockrun_defi$0.0060protocol/chain analysis ($0.0020 for prices/*)
blockrun_chat (free mode)$0NVIDIA-backed chat
blockrun_chat (glm mode)per-tokenZhipu GLM-5 coding — billed on tokens used, not a flat rate
blockrun_exa (search)$0.0110deep research (contents: $0.002/URL + $0.001)
blockrun_speech$0.0535/1k charsTTS
blockrun_image$0.01675–0.106image generation
blockrun_music$0.1585music tracks
blockrun_video$0.421+short video clips (per-second × duration)
blockrun_markets$0.0085prediction market data, wallet analytics (flat)
blockrun_modal$0.0020–$192remote sandbox execution — timeout drives the price, see the modal skill
blockrun_phone$0.0110–$5.001lookups; number buy/renew is $5.001
Show full SKILL.md (169 more words)Show less
Daily Budget Formula (GenTech's Setup)
yaml
# ~$0.30/day typical
Daily budget:
  Free tools:     unlimited (price quotes, dex, list, wallet status)
  Crypto data:   ~$0.10 (markets, flat $0.0085; defi $0.0060; surf is retired and free)
  AI calls:      ~$0.10 (chat free mode, occasional glm)
  Media:         ~$0.10 (occasional image/speech)
  Total:         ~$0.30/day

Set a $5/week budget cap and never hit it with typical usage.


Error Handling Patterns

402 Payment Required
python
# When the wallet is FUNDED, x402 handles this automatically: the SDK
# signs the payment challenge and retries — no action needed.
#
# When the wallet is EMPTY, the 402 / insufficient-balance surfaces to you.
# Check status and fund FIRST — don't blindly retry the failing tool:
blockrun_wallet(action="status")   # then action="setup" / "deposit"
Insufficient Balance
python
# Before a batch of expensive calls:
balance = blockrun_wallet(action="status")
if float(balance["usdcBalance"]) < 0.50:
    blockrun_wallet(action="deposit")  # → opens Coinbase Onramp link
Rate Limiting / Timeouts
python
# For async operations (video, music):
# They auto-poll until complete. On a timeout READ THE ERROR: on the Base
# wallet payment settles on completion, so a timeout is not charged and a
# retry is safe; Solana music and every account-rail media job are billed
# at submit, so the timed-out job IS charged, the error names it, and a
# retry bills a second job. Check blockrun_wallet action:"report" first.

Caching Strategy

BlockRun calls are cheap but not free. Cache results that don't change minute-to-minute:

  • Token prices: No need to cache aggressively — crypto/FX/commodity quotes via blockrun_price are FREE.
  • Protocol TVL: Cache for 1 hour (updates hourly)
  • Wallet labels: Cache for 24 hours (rarely change)
  • On-chain SQL results: Cache for 1 hour (most queries return the same answer)

GenTech's approach: Don't bother caching prices (crypto/FX/commodity quotes are FREE). Cache TVL and wallet labels aggressively.


Switching Chains

python
# Default is Base. Switch to Solana for Solana-native tools:
blockrun_wallet(action="chain", chain="solana")

# Switch back:
blockrun_wallet(action="chain", chain="base")

# Check which is active:
blockrun_wallet(action="chain")

Note: Every paid media tool (image, video, music, speech, realface) pays on either chain. Base-only: blockrun_modal, blockrun_defi, claude-* chat with thinking (a plain claude-* call takes the compat path on Solana), and Polymarket funding. Solana works for price, wallet, dex, rpc, markets, etc.


Reference

Contributed by GenTech Labs, from real production usage of BlockRun MCP.

© BlockRunAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/gentech-blockrun of BlockRunAI/blockrun-mcp.

Open the folder on GitHubat commit e9b2bd5

Compare with similar skills

Gentech Blockrun next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Gentech Blockrun compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Gentech Blockrun this skillBlockRunAI/blockrun-mcp392—~2.5kAutomated safety check: PassMIT
Helius for Solanainternet-court/internet-court-skill6.4k2 repos~2.7kAutomated safety check: PassApache-2.0
Solana Devaiskillstore/marketplace430—~2.4kAutomated safety check: PassMIT
CoinGecko API Reference2025Emma/vibe-coding-cn23k2 repos~646Automated safety check: PassMIT
MCP API Key AuthenticationYourdaylight/stock_datasource188—~1.2kAutomated safety check: PassMIT
Agentmemory REST APIrohitg00/agentmemory29k—~404Automated safety check: PassApache-2.0

Similar skills

  • Helius for Solana

    internet-court/internet-court-skill

    Guides building Solana apps on Helius: sending transactions, asset and NFT queries, live streaming, webhooks, priority fees, wallet analysis and API key onboarding.

    6.4k GitHub starsUsed in 2 repos~2.7k tokens
    Backend & APIsAuto-check passed
  • Solana Dev

    aiskillstore/marketplace

    A skill your agent uses when user asks to "build a Solana dapp", "write an Anchor program", "create a token", "debug Solana errors", "set up wallet connection", "test my Solana program", "deploy to…

    430 GitHub stars~2.4k tokensUpdated yesterday
    Backend & APIsAuto-check passed
  • CoinGecko API Reference

    2025Emma/vibe-coding-cn

    CoinGecko API documentation - cryptocurrency market data API, price feeds, market cap, volume, historical data. Use when integrating CoinGecko API, building…

    23k GitHub starsUsed in 2 repos~646 tokens
    Backend & APIsAuto-check passed
  • MCP API Key Authentication

    Yourdaylight/stock_datasource

    Sets up and troubleshoots MCP API key authentication for a stock data service, covering key creation, client configuration and per-tool usage statistics.

    188 GitHub stars~1.2k tokensUpdated 1 mo ago
    Backend & APIsAuto-check passed
  • Agentmemory REST API

    rohitg00/agentmemory

    Covers the HTTP REST endpoints of the agentmemory server, its primary interface, for hosts without MCP or when MCP is unavailable.

    29k GitHub stars~404 tokensUpdated yesterday
    Backend & APIsAuto-check passed
  • Pyth Network Price Feeds

    internet-court/internet-court-skill

    Shows how to read Pyth oracle prices in Solana apps, off-chain through the Hermes client or on-chain from an Anchor program, including confidence and EMA values.

    6.4k GitHub starsUsed in 2 repos~3.9k tokens
    Backend & APIsAuto-check passed

More from BlockRunAI/blockrun-mcp

All 17 skills in this repo
  • Signal To Trade Demo

    BlockRunAI/blockrun-mcp

    Prepare or run a polished BlockRun trading demo that discovers a current Polymarket market, combines live price, probability history, smart-money, and liquidity evidence into a balanced signal…

    392 GitHub stars~1.8k tokensUpdated today
    Auto-check passed
  • Blockrun

    BlockRunAI/blockrun-mcp

    Pay-per-call access to AI models, real-time data, media generation and multi-chain RPC over x402 micropayments (USDC on Base or Solana), or a BlockRun account API key.

    392 GitHub stars~2.7k tokensUpdated today
    Auto-check passed
  • Blockrun Debug

    BlockRunAI/blockrun-mcp

    A skill your agent uses when the BlockRun MCP server (@blockrun/mcp) is installed but misbehaving — 'Failed to connect', spawn npx ENOENT, blockrun missing from claude mcp list, HTTP 402 /…

    392 GitHub stars~3k tokensUpdated today
    Auto-check passed
  • Blockrun Setup

    BlockRunAI/blockrun-mcp

    A skill your agent uses when asked to install, add, configure, or set up the BlockRun MCP server (@blockrun/mcp) in Claude Code, Claude Desktop, Cursor, Windsurf, Codex CLI, Grok or another MCP…

    392 GitHub stars~2k tokensUpdated today
    Auto-check passed
  • Blockrun Upgrade

    BlockRunAI/blockrun-mcp

    A skill your agent uses when the BlockRun MCP server prints 'Update available', when asked to upgrade, update, or pin @blockrun/mcp, when a fix 'should be in the new version' but the client still…

    392 GitHub stars~1.6k tokensUpdated today
    Auto-check passed
  • Crypto Data

    BlockRunAI/blockrun-mcp

    A skill your agent uses for any crypto data question — token/coin prices, FX, commodities, stocks, OHLC history, DEX pairs and liquidity, DeFi TVL, yield/APY pools, or raw JSON-RPC against a chain…

    392 GitHub stars~2.8k tokensUpdated today
    Auto-check passed

Questions about Gentech Blockrun

What does Gentech Blockrun do?

GenTech Labs' integration patterns for BlockRun MCP from Hermes Agent. Gentech Blockrun is an agent skill from BlockRunAI/blockrun-mcp. GenTech Labs' integration patterns for BlockRun MCP from Hermes Agent.

When should I use Gentech Blockrun?

Gentech Blockrun fits situations like: tasks that involve Third-party API integration; tasks that involve Crypto and DeFi analysis.

How do I install Gentech Blockrun in Claude Code?

Run `npx skills add BlockRunAI/blockrun-mcp --skill gentech-blockrun -a claude-code`. Or copy the skill folder (skills/gentech-blockrun in BlockRunAI/blockrun-mcp) into .claude/skills/gentech-blockrun in your project. Claude Code loads it when a task matches its description.

How do I install Gentech Blockrun in Codex?

Run `npx skills add BlockRunAI/blockrun-mcp --skill gentech-blockrun -a codex`. Or copy the skill folder (skills/gentech-blockrun in BlockRunAI/blockrun-mcp) into .agents/skills/gentech-blockrun in your project. Codex loads it when a task matches its description.

Can I use Gentech Blockrun in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add BlockRunAI/blockrun-mcp --skill gentech-blockrun -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/gentech-blockrun, .gemini/skills/gentech-blockrun, .github/skills/gentech-blockrun and .opencode/skills/gentech-blockrun in your project.

What does Gentech Blockrun need to run?

SKILL.md names no scripts, command-line tools or credentials: Gentech Blockrun is instructions for the agent only. Our summary lists: Python 3.

Does Gentech Blockrun access the network?

SKILL.md names 2 domains. As links in the text: blockrun.ai and t.me. This is read from the text; nothing was executed.

Is Gentech Blockrun safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Gentech Blockrun use?

Gentech Blockrun is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Gentech Blockrun use?

About 2.5k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Gentech Blockrun?

Skills that share tags, products or a category with Gentech Blockrun: Helius for Solana (internet-court/internet-court-skill, 6.4k stars), Solana Dev (aiskillstore/marketplace, 430 stars), CoinGecko API Reference (2025Emma/vibe-coding-cn, 23k stars) and MCP API Key Authentication (Yourdaylight/stock_datasource, 188 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Gentech Blockrun?

BlockRunAI (a GitHub organization) maintains it in BlockRunAI/blockrun-mcp, which has 392 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on October 8, 2026.

Source: BlockRunAI/blockrun-mcp on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.