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 Starchild-ai-agent/official-skills --skill bnbagentgit clone --depth 1 https://github.com/Starchild-ai-agent/official-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/starchild-ai-agent/official-skills/bnbagent)<a href="https://agentmods.dev/skills/starchild-ai-agent/official-skills/bnbagent"><img src="https://agentmods.dev/badge/skills/starchild-ai-agent/official-skills/bnbagent/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/starchild-ai-agent/official-skills/bnbagent"><img src="https://agentmods.dev/badge/skills/starchild-ai-agent/official-skills/bnbagent.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 | $0.00111 | $0.04627 |
| Opus 5 | $0.00056 | $0.02313 |
| Sonnet 5 | $0.00022 | $0.00925 |
| Haiku 4.5 | $0.00011 | $0.00463 |
Grade A, and why
bnbagent 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 12d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
45 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.
- examples/a2a-agent/.env.example 998 B
- examples/a2a-agent/pyproject.toml 271 B
- examples/a2a-agent/README.md 3.0 KB
- examples/a2a-agent/scripts/buyer.py 5.0 KB runs code
- examples/a2a-agent/scripts/register.py 2.6 KB runs code
- examples/a2a-agent/src/server.py 9.2 KB runs code
- examples/agent-server/.env.example 2.0 KB
- examples/agent-server/pyproject.toml 303 B
- examples/agent-server/README.md 6.2 KB
- examples/agent-server/scripts/register.py 5.1 KB runs code
- examples/agent-server/scripts/run_agent_mount.py 334 B runs code
- examples/agent-server/scripts/run_agent.py 1.1 KB runs code
- examples/agent-server/scripts/settle.py 3.8 KB runs code
- examples/agent-server/src/erc8183_server.py 18 KB runs code
- examples/agent-server/src/service_mount.py 9.1 KB runs code
- examples/agent-server/src/service.py 8.5 KB runs code
- examples/auto_settle.py 3.7 KB runs code
- examples/client/_helpers.py 5.8 KB runs code
- examples/client/.env.example 1.8 KB
- examples/client/cancel_open.py 1.1 KB runs code
- examples/client/create_and_verify.py 4.9 KB runs code
- examples/client/dispute_reject.py 2.8 KB runs code
- examples/client/gen_job_report.py 13 KB runs code
- examples/client/happy.py 2.6 KB runs code
- examples/client/never_submit.py 1.6 KB runs code
- examples/client/README.md 5.2 KB
- examples/client/stalemate_expire.py 2.9 KB runs code
- examples/README.md 2.8 KB
- examples/security/e2e.py 9.1 KB runs code
- examples/twak/.env.example 1.8 KB
- examples/twak/e2e_smoke.py 26 KB runs code
- examples/twak/quickstart.py 16 KB runs code
- examples/twak/README.md 4.2 KB
- examples/twak/x402_payer.py 10 KB runs code
- examples/voter/.env.example 399 B
- examples/voter/README.md 2.5 KB
- examples/voter/vote_reject.py 2.8 KB runs code
- examples/voter/watch.py 7.1 KB runs code
- examples/x402/buyer_demo.py 12 KB runs code
- logo.png 9.3 KB
- references/architecture.md 20 KB
- references/env.example 4.0 KB
- references/sdk-readme.md 33 KB
- references/twak.md 10 KB
- references/wallets.md 31 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.
- 12d ago First seen · 250 lines · 111 tokens per session scan A 01ef0b467bb5
bnbagent is a skill published in the GitHub repository Starchild-ai-agent/official-skills (27 stars, last pushed yesterday), with no licence file. It adds 111 tokens to every session and 4,627 once invoked, about $0.0006 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 skills, from other repositories
signature-replay
Signature replay attacks — missing nonces, missing chain ID, ecrecover zero address, signature malleability, cross-chain replay.
official-sui-skills
Pointer to the official Mysten Labs skills for building on Sui — language fundamentals, object model, PTBs, SDKs, publishing, upgrades, frontend integration, accessing on-chain data. Maintained upstream at github.com/MystenLabs/skills; pinned to the same ref the audit catalog derives from (see…
bridge
Cross-chain token transfers using Wormhole and CCTP.
onchainkit
Build onchain apps with Coinbase's OnchainKit React components - wallets, swaps, NFTs, payments.
marginfi
MarginFi — Solana lending and borrowing.
crypto-market-rank
Crypto market rankings and leaderboards. Query trending tokens, top searched tokens, Binance Alpha tokens, tokenized stocks, social hype sentiment ranks, smart money inflow token rankings, top meme token rankings from Pulse launchpad, and top trader PnL leaderboards. Use this skill when users ask about token rankings…