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/oh-rid/claude-code-plugin-ib/ib-referencenpx skills add oh-rid/claude-code-plugin-ib --skill ib-referencegit clone --depth 1 https://github.com/oh-rid/claude-code-plugin-ibWhat 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 | $0.00123 | $0.04974 |
| Opus 5 | $0.00062 | $0.02487 |
| Sonnet 5 | $0.00025 | $0.00995 |
| Haiku 4.5 | $0.00012 | $0.00497 |
Grade A, and why
ib-reference 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 — 410 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interactive Brokers Reference
Quick-scan reference for avoiding common mistakes when working with IB data.
TOP AGENT MISTAKES
| # | Mistake | Reality |
|---|---|---|
| 1 | Guessing what a futures ticker means | IB futures symbols are NOT obvious. MET = Micro Ether, NOT Micro E-mini. MSL = Micro SOL (Solana), NOT Micro Silver. SIL = Micro Silver. MES = Micro E-mini S&P. ALWAYS verify on cmegroup.com before interpreting. |
| 2 | Treating MTM P&L as net profit | MTM shows commissions as separate line. FIFO includes them in cost basis. You MUST subtract commissions from MTM to get true net. |
| 3 | Ignoring multiplier for derivatives |
Options: multiply by 100 (usually). Futures: contract-specific. Formula: quantity * price * multiplier = value. |
| 4 | Applying fxRateToBase wrong |
It is a multiplier: amount_in_trade_ccy * fxRateToBase = amount_in_base_ccy. NOT a divisor. |
| 5 | Assuming one timezone | IB uses exchange-local for P&L reset, EST for statement cutoffs, no single "IB timezone". |
| 6 | Confusing Ending Cash with available money | Ending Cash = trade-date basis (includes unsettled). Ending Settled Cash = what you actually have. Interest accrues on settled only. |
| 7 | Misreading Closed Lots <Lot> schema |
tradePrice in <Lot> is the OPEN price, NOT the close price. cost = opening cost basis. buySell = closing trade direction universally (SELL=closed long, BUY=closed short) — same rule for STK, OPT, FOP, FUT. Close price is NOT stored — derive from realized. Always cross-check interpretation against Activity Flex (executions-level) before trusting Closed Lots labels. |
| 8 | Assuming account base is USD | Many EU accounts have base = EUR. Check Account Information section or read CashReport BASE_SUMMARY. When base IS EUR, fxRateToBase for a USD trade is ~0.85-0.88 ("1 USD → N EUR"). |
FLEX WEB SERVICE
How It Works (Two-Step)
Step 1 — SendRequest:
GET https://ndcdyn.interactivebrokers.com/AccountManagement/FlexWebService/SendRequest
?t={TOKEN}&q={QUERY_ID}&v=3
Returns XML with <ReferenceCode>. Optional: &fd=yyyymmdd&td=yyyymmdd for date override, &p={DAYS} for period.
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 · 410 lines · 123 tokens per session scan A 7b20ac352445
ib-reference is a skill published in the GitHub repository oh-rid/claude-code-plugin-ib (5 stars, last pushed 3mo ago), licensed MIT. It adds 123 tokens to every session and 4,974 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…