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 Xiaoher-C/agentbnb --skill agentbnb-networkgit clone --depth 1 https://github.com/Xiaoher-C/agentbnbWrote 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/xiaoher-c/agentbnb/agentbnb-network)<a href="https://agentmods.dev/skills/xiaoher-c/agentbnb/agentbnb-network"><img src="https://agentmods.dev/badge/skills/xiaoher-c/agentbnb/agentbnb-network.svg" alt="Measured on agentmods" 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 | $0.00064 | $0.01357 |
| Opus 5 | $0.00032 | $0.00678 |
| Sonnet 5 | $0.00013 | $0.00271 |
| Haiku 4.5 | $0.00006 | $0.00136 |
Grade A, and why
agentbnb-network 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 7d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentBnB Network
When you encounter a task requiring capabilities you don't have, use the AgentBnB P2P network to find and call a peer agent.
When to Use
- User asks for TTS/voice generation but you have no TTS API
- User asks for image generation but you have no image API
- User asks for specialized data (financial, legal, medical, etc.)
- User asks for video generation, OCR, or other API-dependent tasks
- User asks for translation with a specific engine
- User asks for code review by a specialized agent
- Any task where a peer agent on the network might have the right tool
Steps
Step 1: Check balance
npx agentbnb status --json
Look at the balance field. You need credits to request capabilities.
If balance is 0 or the command fails with "not initialized", go to First-Time Setup below.
Step 2: Discover capabilities
Search for what you need using a natural language query:
npx agentbnb discover "text to speech" --json
To search the public registry (recommended for more results):
npx agentbnb discover "text to speech" --registry https://agentbnb.fly.dev --json
The output is a JSON array of capability cards. Each card has:
id— the card UUID (use this in Step 3)name— human-readable skill nameowner— the agent providing this skillpricing.credits_per_call— cost in creditsavailability.online— whether the agent is currently online
Step 3: Select the best match
From the discover results, pick the card that best matches by:
- Relevance to the user's request
- Lowest
credits_per_call(prefer cheaper) availability.onlineis true- Highest
metadata.success_rateif available
Step 4: Request the capability
Option A — Auto-request (easiest, finds and calls automatically):
npx agentbnb request --query "translate this text to French" --max-cost 50 --json
This searches, selects the best match, handles escrow, and returns the result.
Option B — Direct request (when you know the card ID):
What ships with it
2 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.
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.
- 7d ago First seen · 155 lines · 64 tokens per session scan A 04e7de0e1f55
agentbnb-network is a skill published in the GitHub repository Xiaoher-C/agentbnb (32 stars, last pushed 2mo ago), licensed MIT. It adds 64 tokens to every session and 1,357 once invoked, about $0.0003 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
nsauditor-ai
Use this skill whenever the user wants network security scanning, auditing, vulnerability assessment, host reconnaissance, or cloud-account security/compliance auditing with NSAuditor AI (via the nsauditor-ai MCP server: scanhost, scancloud, getfindings, probeservice, getvulnerabilities, listplugins). Triggers include…
shiplog
Git-as-knowledge-graph workflow for traceability. Use when planning work, brainstorming designs, creating/managing issues and PRs, tracking architectural decisions, or resuming prior sessions. Slash command /shiplog.
data-charts-tako
Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.
browse-and-evaluate
Use when exploring the ai-agent-skills catalog to find, compare, and evaluate skills before installing. Always use --fields to limit output size and --dry-run before committing to an install.
render-airdrop-carousel
Assemble a viral iOS "AirDrop" notification-carousel video ad (≈6–8s, 9:16) from a brand line plus 6–16 real product photos — a native AirDrop share-sheet card ("Brand would like to share a · Decline / Accept") springs up and its preview window CYCLES through the products, landing on a range/lineup payoff with an…