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-isolated-marginnpx skills add crypto-com/cdcx-cli --skill cdcx-isolated-margingit clone --depth 1 https://github.com/crypto-com/cdcx-cliWhat 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 | $0.00049 | $0.02304 |
| Opus 5 | $0.00024 | $0.01152 |
| Sonnet 5 | $0.00010 | $0.00461 |
| Haiku 4.5 | $0.00005 | $0.00230 |
Grade A, and why
cdcx-isolated-margin 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 2d 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 — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Isolated Margin
When to Use
Some instruments — notably equity/RWA perpetuals such as SPYUSD-PERP and NVDAUSD-PERP — cannot be traded on the default cross-margin account. Attempting to do so returns:
{
"code": 623,
"message": "INSTRUMENT_MUST_USE_ISOLATED_MARGIN"
}
Isolated margin puts the position in its own margin bucket with its own leverage. Losses are capped at the isolated balance; a wipeout on one position cannot cascade into cross-margin balances on other instruments.
Use isolated margin when:
- The exchange requires it (error
623). - You want per-position risk isolation (e.g. high-leverage directional bet).
- You want a distinct leverage setting on one instrument without changing your cross-account config.
Do not use isolated margin for:
- Spot pairs (
CCY_PAIR) — not applicable. - Crypto perpetuals where you want shared collateral across positions.
One Position Per Instrument
The exchange enforces one isolated position per instrument per account. You cannot open two separate isolated buckets on SPYUSD-PERP — the second order must reference the first position's isolation_id so the exchange knows whether you're adding to, trimming, or reversing it.
To top up or trim an open isolated position:
- Look up its
isolation_idviacdcx account positions -o json(or theuser.positionsWS channel). - Include
--isolation-id <ID>on the nextcdcx trade ordercall.
Omitting --isolation-id on a second order returns:
{
"code": 617,
"message": "DUPLICATED_INSTRUMENT_ORDER_FOR_ISOLATED_MARGIN"
}
TUI Workflow
Open the place-order modal (t on the Market tab) and use the Margin row:
Inst: SPYUSD-PERP
Side: [BUY] SELL
Type: [LIMIT] MARKET
Margin: [ISOLATED] CROSS (M to toggle)
Price: 710.25
Qty: 0.001
←/→orSpacewhile on the Margin row, orMfrom anywhere in the modal (except free-text fields), flipsISOLATED ↔ CROSS.- Isolated margin is pre-selected automatically for instruments whose
inst_typerequires it (e.g. equity perpetuals). - On success, the toast reads
Order placed (isolated margin)so the mode is unambiguous. - The TUI subscribes to
user.positionsat startup (when authenticated) soisolation_idfor any open isolated position is cached and auto-attached to your next order on the same instrument. You do not need to supply it manually in the TUI.
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.
- 2d ago First seen · 232 lines · 49 tokens per session scan A 5d4dd89a17b2
cdcx-isolated-margin is a skill published in the GitHub repository crypto-com/cdcx-cli (25 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 49 tokens to every session and 2,304 once invoked, about $0.0002 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.