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.
npx agentmods add skills/cgyudistira/agentkit/blockrunnpx skills add cgyudistira/agentkit --skill blockrungit clone --depth 1 https://github.com/cgyudistira/agentkitWhat 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 | $0.00049 | $0.02484 |
| Opus 5 | $0.00024 | $0.01242 |
| Sonnet 5 | $0.00010 | $0.00497 |
| Haiku 4.5 | $0.00005 | $0.00248 |
Grade A, and why
blockrun 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 2d 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 — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BlockRun
BlockRun works with Claude Code and Google Antigravity.
You can't generate images. You have no real-time X/Twitter access. BlockRun gives you these capabilities.
Philosophy
You have a wallet. When you need a capability you lack, you pay for it autonomously.
| You Need | You Call | Pricing |
|---|---|---|
| Image generation | DALL-E | $0.04/image |
| Real-time X data | Grok + Live Search | $0.025/source |
| Second opinion | GPT-5.2 | $1.75/M input, $14/M output |
| Cheaper processing | DeepSeek | $0.14/M input, $0.28/M output |
How it works: BlockRun uses x402 micropayments to route your requests to OpenAI, xAI, Google, and other providers. No API keys needed - your wallet pays per token.
Budget Control (Optional)
If the user specifies a budget (e.g., "use at most $1"), track spending and stop when budget is reached:
from blockrun_llm import setup_agent_wallet
client = setup_agent_wallet()
budget = 1.0 # User's budget
# Before each call, check if within budget
spending = client.get_spending()
if spending['total_usd'] >= budget:
print(f"Budget reached: ${spending['total_usd']:.4f} spent")
# Stop making calls
else:
response = client.chat("openai/gpt-5.2", "Hello!")
# At the end, report spending
spending = client.get_spending()
print(f"💰 Total spent: ${spending['total_usd']:.4f} across {spending['calls']} calls")
When to Use
| Trigger | Your Action |
|---|---|
| User explicitly requests ("blockrun second opinion with GPT on...", "use grok to check...", "generate image with dall-e") | Execute via BlockRun |
| User needs something you can't do (images, live X data) | Suggest BlockRun, wait for confirmation |
| You can handle the task fine | Do it yourself, don't mention BlockRun |
Example User Prompts
Users will say things like:
| User Says | What You Do |
|---|---|
| "blockrun generate an image of a sunset" | Call DALL-E via ImageClient |
| "use grok to check what's trending on X" | Call Grok with search=True |
| "blockrun GPT review this code" | Call GPT-5.2 via LLMClient |
| "what's the latest news about AI agents?" | Suggest Grok (you lack real-time data) |
| "generate a logo for my startup" | Suggest DALL-E (you can't generate images) |
| "blockrun check my balance" | Show wallet balance via get_balance() |
| "blockrun deepseek summarize this file" | Call DeepSeek for cost savings |
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.
- 2d ago First seen · 293 lines · 49 tokens per session scan A f1658d2cde53
blockrun is a skill published in the GitHub repository cgyudistira/agentkit (2 stars, last pushed 6mo ago), licensed MIT. It adds 49 tokens to every session and 2,484 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 2026-08-31.
Other skills, from other repositories
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
bigquery-ai-ml
Leverages BigQuery's built-in machine learning and GenAI capabilities for advanced data analytics. Use when you need to write SQL queries that perform time-series forecasting, predict values, detect outliers or anomalies, find key drivers, perform semantic search or vector search, classify text, calculate similarity…
ondb
A logical analysis and reasoning tool for AI. Use when decomposing documents into structured knowledge, querying entities and relations, validating consistency, or indexing files. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", "analyze this document", entity CRUD, or cross-skill…
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
mixed-precision
Use FP16/BF16 mixed precision to accelerate training and reduce memory. Use when optimizing GPU performance.
sparse-autoencoder-training
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.