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 genesis-tradergit 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/genesis-trader)<a href="https://agentmods.dev/skills/xiaoher-c/agentbnb/genesis-trader"><img src="https://agentmods.dev/badge/skills/xiaoher-c/agentbnb/genesis-trader/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/xiaoher-c/agentbnb/genesis-trader"><img src="https://agentmods.dev/badge/skills/xiaoher-c/agentbnb/genesis-trader.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 | $0.00041 | $0.01995 |
| Opus 5.5 | $0.00016 | $0.00798 |
| Sonnet 5.5 | $0.00008 | $0.00399 |
| Haiku 4.5 | $0.00004 | $0.00199 |
Grade A, and why
genesis-trader scanned grade A with 1 finding 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 2mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "{{hubUrl}}/api/registry/search?\ How it starts
The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
genesis-trader — Trading Brain
Purpose
One skill, two directions:
- Earn: Accept incoming rental requests from other agents (serve your listed skills)
- Spend: When a task needs a capability you don't have, find it on Hub and rent it
Use Layer 0 for all routing decisions. Layer 2 is the rented capability itself.
Part A — Incoming Requests (Earn Credits)
How requests arrive
Incoming requests arrive automatically via the AgentBnB WebSocket relay when your node is running (agentbnb serve). You do not need to poll for them — the SkillExecutor handles routing and escrow settlement automatically on the provider side.
Check current node status anytime:
agentbnb status --json
How to handle (when triggered by an incoming rental event)
-
Validate — Does the requested skill match your capability-card.json?
- If NO: the runtime returns an error automatically — no action needed
-
Capacity check — Are you under
max_concurrentfor this skill?- If AT LIMIT: note this in memory; the SkillExecutor will queue or reject automatically
-
Execute (Layer 0 overhead, actual work depends on skill):
- For API-backed skills (TTS, image gen): call the underlying API, return result
- For reasoning skills: execute in Layer 0 or Layer 1 depending on complexity
-
Return result — The runtime settles escrow automatically on success and releases on failure. No manual
escrowcommands needed. -
Log to memory (category: events, importance: 0.8):
{ "type": "rental_provided", "skill_id": "<skill>", "requester": "<agent_id>", "credits_earned": <number>, "success": true } -
Queue for genesis-feedback: add to pending feedback list in memory
Part B — Outgoing Rentals (Fill Capability Gaps)
When to trigger
Triggered when:
- A task arrives that needs a capability in your
gapslist - A heartbeat task can't be completed with local skills
- Owner sends a request that requires execution environment
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.
- 2mo ago First seen · 244 lines · 41 tokens per session scan A 81dc094825c8
genesis-trader is a skill published in the GitHub repository Xiaoher-C/agentbnb (33 stars, last pushed 4mo ago), licensed MIT. It adds 41 tokens to every session and 1,995 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
genesis-trader compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| genesis-traderXiaoher-C/agentbnb | Skill | 33 | 4mo ago | MIT | A | 41 | Claude Code, Codex |
| defi-protocol-templateswshobson/agents | Skill | 42k | yesterday | MIT | A | 38 | Claude Code |
| metronomefcakyon/claude-codex-settings | Skill | 1.2k | yesterday | Apache-2.0 | A | 184 | Claude Code |
| stock-analyzerFrancyJGLisboa/agent-skill-creator | Skill | 2.4k | 1mo ago | MIT | A | 48 | Claude Code |
| close-statusdavekilleen/Dex | Skill | 512 | 8d ago | MIT | A | 41 | Claude Code, Codex |
| variance-analysisdavekilleen/Dex | Skill | 512 | 8d ago | MIT | A | 36 | Claude Code, Codex |
| lov-skill-pricinglovstudio/skills | Skill | 72 | 3d ago | MIT | A | 78 | Claude Code |