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 INo-xious/stockbit-mcp --skill bandar-checkgit clone --depth 1 https://github.com/INo-xious/stockbit-mcpWrote 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/ino-xious/stockbit-mcp/bandar-check)<a href="https://agentmods.dev/skills/ino-xious/stockbit-mcp/bandar-check"><img src="https://agentmods.dev/badge/skills/ino-xious/stockbit-mcp/bandar-check/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/ino-xious/stockbit-mcp/bandar-check"><img src="https://agentmods.dev/badge/skills/ino-xious/stockbit-mcp/bandar-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00054 | $0.01175 |
| Opus 5.5 | $0.00022 | $0.00470 |
| Sonnet 5.5 | $0.00011 | $0.00235 |
| Haiku 4.5 | $0.00005 | $0.00118 |
Grade A, and why
bandar-check 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bandar check
Broker flow is the one thing this server has that no general market API does. It is also the easiest thing to over-read, so the order below is not optional: establish that the tape is meaningful before saying anything about who is on it.
The sequence
market_session— is the market open, pre-open, or closed? Today's flow is partial until it closes. Say so rather than quietly presenting half a day as a day.broker_summary symbol=…— the ledger. Every broker's buy and sell over the window.periodtakes one of FIVE windows, and only these five:LATEST,YESTERDAY,LAST_7_DAYS,LAST_3_MONTHS,YEAR_TO_DATE. The longer ten-value list belongs tobroker_topandbroker_distribution, which are different endpoints; sending one of those here is rejected, andLAST_1_DAY/LAST_30_DAYSreturn a 400 from Stockbit itself. Or givefrom/tofor an explicit range. Do not do both — the API ignores the dates and answers with the latest session, silently.broker_activityhas no window at all. Measured 2026-09-01: every value ofperiodanswers 400 there, so the tool refuses it rather than sending it. Its window is the server's, and it is reported back infrom/toon the result — read those to date the rows.transaction_typeisNETorGROSS. NET is the question people mean. GROSS tells you who was busy; NET tells you who ended up holding.market_boarddefaults to the regular board.NEGOandTUNAIare crossings and cash settlement — real, but not the same signal. If the user's question is about accumulation, say which board the number came from.investor_typesplits Asing (foreign), Lokal (domestic) and Pemerintah (government).
broker_distribution symbol=…— who bought from whom. This is the part that turns a list of names into a story: it pairs the accumulating brokers with the ones supplying them.bandar_detector symbol=…for a ranked read, orbroker_activity broker_code=…to ask the opposite question — what else has this broker been doing.- In the ranked read,
topDistributorsis largest seller FIRST, and sell figures are NEGATIVE because that is how the wire sends them. Do not negate them again.
- In the ranked read,
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 Changed · +3 lines 40c18e998c8b
- 1mo ago First seen · 69 lines · 54 tokens per session scan A 51587ad3665a
bandar-check is a skill published in the GitHub repository INo-xious/stockbit-mcp (56 stars, last pushed 8d ago), licensed MIT. It adds 54 tokens to every session and 1,175 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
tradingview-mcp
AI Trading Intelligence — live prices, 30+ technical indicators, backtesting (6 strategies), walk-forward overfitting detection, trade logs, equity curves, licensed news sentiment (Marketaux), and multi-market screener. Supports stocks, crypto, ETFs, indices, Turkish (BIST), and Egyptian (EGX) markets.
escalation
Escalate a disputed refund to the billing lead.
refunds
Process customer refunds.
error-handling
Read the error codes these tools raise and decide whether to retry, fix the call, or stop.
issue-management
Create, update, list and search GitHub issues and PRs, list a repository's labels, run milestones, and check for duplicates.
release-management
Tag a commit, publish a GitHub release, and read, correct or withdraw the tags and releases already there.