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 agentmods add skills/crypto-com/cdcx-cli/cdcx-autonomy-levelsnpx skills add crypto-com/cdcx-cli --skill cdcx-autonomy-levelsgit clone --depth 1 https://github.com/crypto-com/cdcx-cliWrote 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/crypto-com/cdcx-cli/cdcx-autonomy-levels)<a href="https://agentmods.dev/skills/crypto-com/cdcx-cli/cdcx-autonomy-levels"><img src="https://agentmods.dev/badge/skills/crypto-com/cdcx-cli/cdcx-autonomy-levels.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 | $0.00029 | $0.00902 |
| Opus 5 | $0.00015 | $0.00451 |
| Sonnet 5 | $0.00006 | $0.00180 |
| Haiku 4.5 | $0.00003 | $0.00090 |
Grade A, and why
cdcx-autonomy-levels 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 5d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autonomy Levels
Philosophy
Agents should operate at the lowest autonomy level that accomplishes their task. Each level upward trades human oversight for agent independence.
Safety Tiers (the underlying mechanism)
Every cdcx MCP tool is classified into one of four tiers:
| Tier | Agent Behaviour | Example |
|---|---|---|
read |
Runs freely, no acknowledgement | cdcx_market_ticker |
sensitive_read |
Runs freely, no acknowledgement | cdcx_account_summary |
mutate |
Requires acknowledged: true in tool arguments |
cdcx_trade_order |
dangerous |
Refused unless server was started --allow-dangerous |
cdcx_trade_cancel_all, cdcx_funding_withdraw |
Level 0 — Read-only
Agent can observe the market but cannot touch the account.
cdcx mcp config --reset # ensures only market is enabled
Use for: market research agents, price alerts, chart commentary.
Level 1 — Paper
Agent can read live market data plus read authenticated account info; any actual trading is paper-only and handled CLI-side (not via MCP).
cdcx mcp config --enable account
Pair the MCP server with shell access to cdcx paper for simulated execution. Paper has no MCP tools; execution stays outside the agent's tool surface.
Use for: strategy research with real account context, backtest harnesses.
Level 2 — Supervised Live
Agent can place and cancel real orders, but every mutation requires explicit acknowledgement from the host application (human-in-the-loop).
cdcx mcp config --enable account,trade,advanced
The agent calls cdcx_trade_order; the host MUST echo the intent to the human and only pass acknowledged: true once approved. Dangerous tools (cancel-all, withdraw) are refused at the server since allow_dangerous is not set.
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.
- 5d ago First seen · 92 lines · 29 tokens per session scan A 279b2f075102
cdcx-autonomy-levels is a skill published in the GitHub repository crypto-com/cdcx-cli (25 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 29 tokens to every session and 902 once invoked, about $0.0001 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
sector-rotation
行业轮动分析——申万行业景气度评分、行业动量排名、产业链传导、估值/盈利/资金流多维比较框架.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
chenhao-limit-up
Use when evaluating A-share limit-up (涨停板) setups through Chen Hao's sentiment and momentum lens: market emotion cycles, board strength, follow-through, and short-term aggressive momentum trading.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
multi-expert-analyzer
针对通用问题进行多领域专家联合分析, 综合稿产生前必经 fact-checker 与 red-team 两道独立校验。适用场景: 用户提出跨领域或不确定领域的复杂问题, 需要从多个专家角度分别搜证并相互校验后综合成文, 例如该不该买房、该不该跳槽、是否进入某个赛道等。触发关键词: 多角度分析、专家分析、综合分析、多视角、跨领域分析、从不同角度看、深度分析。问题只属于单一明确领域时, 优先使用该领域的专门 skill, 例如纯财务用 finance-core-analysis、纯技术用 software-architect。输出 (全部 markdown 保存到当前项目 markdown/ 目录): (1) 每位专家的中间分析稿…