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 skills add bnb-chain/bnbchain-skills --skill bnbagent-studiogit clone --depth 1 https://github.com/bnb-chain/bnbchain-skillsWrote 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/skills/bnb-chain/bnbchain-skills/bnbagent-studio)<a href="https://agentmods.dev/skills/bnb-chain/bnbchain-skills/bnbagent-studio"><img src="https://agentmods.dev/badge/skills/bnb-chain/bnbchain-skills/bnbagent-studio/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/skills/bnb-chain/bnbchain-skills/bnbagent-studio"><img src="https://agentmods.dev/badge/skills/bnb-chain/bnbchain-skills/bnbagent-studio.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 | $0.00214 | $0.03321 |
| Opus 5 | $0.00107 | $0.01661 |
| Sonnet 5 | $0.00043 | $0.00664 |
| Haiku 4.5 | $0.00021 | $0.00332 |
Grade A, and why
bnbagent-studio 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 yesterday.
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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bnbagent-studio (the single entry point)
bnbagent-studio (CLI: bag) wires the @bnbagent/sdk protocol layer (wallet / ERC-8004 / ERC-8183 / Pieverse LLM) into a TypeScript agent project, then deploys it as a single blockchain seller runtime. A2A, MCP, and X402 are composable public faces selected with --protocols; every wallet kind scaffolds A2A + X402 with both ERC-8183 and B402 rails by default (for altana the paid B402 payout lands at the admin address). bag deploy uses scheme C: every new deploy or redeploy explicitly selects BNB, AWS, Azure, or CreateOS; a recorded deployment is used only to offer an explicit update action, never as a silent default. BNB is a 48h testnet trial and is disabled after expiry. AWS and Azure self-deploy into the user's own account. All cloud lifecycle mutations go through the pinned deploy packages (NodeOps uses their Node.js SDK); the optional AWS CLI is used only by the fail-open, read-only AgentCore quota check in bag deploy prepare. AgentCore and Azure Foundry share the unified A2A/X402 entrypoint; Azure rejects MCP. Treat an incompatible provider row as unavailable-do not force through it or mutate the scaffold during deploy.
Invoked as /bnbagent-studio <ask>? Treat <ask> as the user's intent and route it through the decision tree below, exactly like a natural-language ask.
Runtime preflight
This skill requires bag 0.0.14 or newer. Before following any workflow,
run the read-only command bag --version. If bag is missing or older, stop
and ask the user to run npm install -g @bnbagent/studio-cli@latest, then
repeat the version check. Never install or upgrade a global executable without
the user's approval.
The single seller runtime model (the invariants)
One deployed runtime, one signer: a single valuable Agent serves the selected faces (A2A src/unifiedMain.ts on :9000, MCP src/mcpMain.ts on :8000/mcp, or A2A-native src/dualMain.ts on :9000 with tunneled /mcp), holds the key, and signs in-process. The ERC-8183 rail exposes exactly two bounded operations - negotiate (deterministic canonical USD price conversion + EIP-191 sign; no LLM touches money) and notify_funded (verify the funded job → produce the deliverable → submit on-chain; A2A acks then delivers in the background, MCP delivers synchronously in the tool call). The optional x402 rail adds an anonymous HTTP request at /x402; positive prices settle through B402 before work, while explicit zero is FREE passthrough and bypasses the facilitator. It does not expose a general signing tool. Read-only chain tools remain available. ALL signing is fixed entrypoint code in app/agent/src/signing.ts or the runtime's bounded x402 payment handler, never an LLM-callable tool. The encrypted keystore lives at the workspace root .studio/wallets/, outside the deploy codeLocation, and is injected only via the selected provider's delegated secret channel. settle is manual (bag erc8183 settle). Full layout and lifecycle details live in the references below - read them before acting.
What ships with it
16 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/bnbagent-studio-adding-to-project.md 14 KB
- references/bnbagent-studio-buying-from-bazaar.md 9.9 KB
- references/bnbagent-studio-buying-via-8183.md 12 KB
- references/bnbagent-studio-buying-via-mpp.md 3.2 KB
- references/bnbagent-studio-extending-signing.md 12 KB
- references/bnbagent-studio-operating.md 17 KB
- references/bnbagent-studio-scaffolding-agent.md 38 KB
- references/bnbagent-studio-selling-via-8183.md 20 KB
- references/bnbagent-studio-selling-via-b402.md 15 KB
- references/bnbagent-studio-use-aws-agentcore.md 14 KB
- references/bnbagent-studio-use-azure-foundry.md 13 KB
- references/bnbagent-studio-use-bnb-trial.md 4.6 KB
- references/bnbagent-studio-use-createos.md 23 KB
- references/bnbagent-studio-using-altana-wallet.md 5.6 KB
- references/bnbagent-studio-using-twak-wallet.md 13 KB
- references/bnbagent-studio-wiring-llm-tools.md 14 KB
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.
- yesterday First seen · 84 lines · 214 tokens per session scan A bd5a25f8341f
bnbagent-studio is a skill published in the GitHub repository bnb-chain/bnbchain-skills (65 stars, last pushed 2d ago), licensed MIT. It adds 214 tokens to every session and 3,321 once invoked, about $0.0011 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 2026-09-21.
Other skills, from other repositories
cli-anything-eth2-quickstart
Use eth2-quickstart to autonomously deploy a hardened Ethereum node, install execution and consensus clients, configure validator metadata, expose RPC safely, and inspect node health with structured JSON output.
devloop
Goal-driven development loop — define objective, write rules with key-results, verify visually, sync to issue tracker.
skill0
Root index of x-cmd skill0 sub-skills. Defines the OKR-style agent workflow (goal → rule-verified results → execute), skill discovery, and agent tooling preferences. Style: principle-first, concise, delegate specifics to authoritative external sources.
multichain-deployment
Use when deploying the same protocol to multiple chains at the same address. Covers CREATE2 for deterministic addresses, deployment registries, chain-specific configuration, multi-chain testing, and canonical deployment patterns.
l2-deployment
Use when deploying contracts to L2 networks (Base, Optimism, Arbitrum). Covers L2-specific considerations, PUSH0 compatibility, gas estimation, L1 data costs, bridge integration, and deployment scripts.
blockchain-infrastructure
Use this skill when asked about blockchain node deployment, RPC infrastructure, CI/CD for smart contracts, monitoring and alerting for blockchain networks, MEV infrastructure (Flashbots, builders, relays), key management (KMS, HSM), and environment management for devnet/testnet/staging/mainnet. Languages: Go, Rust…