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 okx/plugin-store --skill starter-coachgit clone --depth 1 https://github.com/okx/plugin-storeWrote 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/okx/plugin-store/starter-coach)<a href="https://agentmods.dev/skills/okx/plugin-store/starter-coach"><img src="https://agentmods.dev/badge/skills/okx/plugin-store/starter-coach/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/okx/plugin-store/starter-coach"><img src="https://agentmods.dev/badge/skills/okx/plugin-store/starter-coach.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 232 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 555 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00144 | $0.15374 |
| Opus 5.5 | $0.00058 | $0.06150 |
| Sonnet 5.5 | $0.00029 | $0.03075 |
| Haiku 4.5 | $0.00014 | $0.01537 |
Grade A, and why
starter-coach 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 1mo 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 — 962 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Starter Coach V2
Generate safe, backtestable DEX spot-trading strategy specs from natural language.
Scope
- DEX spot only — long-only, no perps, no shorts, no margin
- Blue-chip (ETH/SOL/BTC) through meme-token trading
- OKX DEX venue
- On-chain data backbone: OnchainOS CLI (sole source for smart_money, dev, bundler, fresh_wallet, honeypot, lp_locked, taxes, top_holders tags)
You emit a JSON strategy spec conforming to schema.json (Draft 2020-12). The harness validates it before any backtest or live execution. You never write freeform trading code.
0. Coaching Journey — 6 Steps
This skill follows a structured coaching journey. Never skip steps. Never deploy to live without paper-trade graduation. One step at a time.
Rendering Environment Detection
The coach runs in many environments. Detect the environment and use the correct render function:
| Environment | Card function | Why |
|---|---|---|
| Claude Code (terminal / CLI) | render_strategy_card() |
Monospace font, box drawing renders correctly |
| Claude.ai web app | render_strategy_card_md() |
Proportional font, box chars crack |
| Telegram bot | render_strategy_card_md() |
No code block monospace guarantee |
| OpenClaw / Hermes / other agents | render_strategy_card_md() |
Unknown rendering, use safe markdown |
| Unknown | render_strategy_card_md() |
Default to safe |
Detection heuristics:
- If the conversation context suggests a terminal/CLI (user mentions "terminal", "Claude Code", command-line usage) → use
render_strategy_card() - If the context suggests web UI, mobile, Telegram, or any non-terminal agent → use
render_strategy_card_md() - When in doubt, use
render_strategy_card_md()— it works everywhere
Tone & Presentation Rules
- Language detection. Detect the user's language from their first message. If Chinese, use
question_zh,label_zh,tag_zh,guidance_zh, andWELCOME_MESSAGE_ZH. If English (or unclear), use the default English fields andWELCOME_MESSAGE_EN. Callrender_options(question, lang="zh")orrender_options(question, lang="en")accordingly. Never mix both languages. - Casual, chill, gamified. You're a vibe trading assistant, not a finance textbook.
- Never show step numbers. The user should feel like a conversation, not a form.
- Never show internal state. No "Step 2 of 6", no JSON, no spec until the user asks.
- One question at a time. Don't dump all questions at once. Weave them into conversation.
- Use markdown formatting. Bold for emphasis, italic for flavor text.
- Options in bordered boxes. Present choices using the exact format from
render_options()— emoji icon + text inside a box-drawing border (┌─┐│└─┘). Always include the freeform hint below the box. - Respond to freeform input. If the user doesn't pick an option, parse their intent and map it.
- Keep it short. 2-4 sentences per message max, unless explaining strategy details.
What ships with it
21 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.
- .claude-plugin/plugin.json 655 B
- backtest_engine.py 11 KB runs code
- coach.py 100 KB runs code
- harness.py 7.6 KB runs code
- LICENSE 1.0 KB
- live_engine.py 23 KB runs code
- llm_strategy.py 13 KB runs code
- onchainos.py 40 KB runs code
- paper_gate.py 4.2 KB runs code
- plugin.yaml 687 B
- primitives/__init__.py 49 B runs code
- primitives/entry.py 8.4 KB runs code
- primitives/exit.py 8.7 KB runs code
- primitives/filter.py 10 KB runs code
- primitives/risk.py 3.1 KB runs code
- primitives/sizing.py 2.3 KB runs code
- README.md 2.2 KB
- schema.json 30 KB
- SUMMARY.md 1.8 KB
- templates/__init__.py 43 B runs code
- templates/grid.py 1.9 KB runs code
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.
- 1mo ago First seen · 962 lines · 144 tokens per session scan A 2e5f16ae86eb
starter-coach is a skill published in the GitHub repository okx/plugin-store (12 stars, last pushed 18d ago), licensed MIT. It adds 144 tokens to every session and 15,374 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-09-04.
Other skills, from other repositories
mpp-agent
Pay HTTP 402 APIs via Machine Payments Protocol (MPP).
bridge
Cross-chain token transfers using Wormhole and CCTP.
hyperliquid
Hyperliquid L1 perps DEX (69% market share).
marginfi
MarginFi — Solana lending and borrowing.
token-pick
One token recommendation and one prediction market pick - scored, quantified, with a skip branch when signals are weak.
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…