Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/INo-xious/stockbit-mcpnpx agentmods add skills/ino-xious/stockbit-mcp/watchWrote 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/watch)<a href="https://agentmods.dev/skills/ino-xious/stockbit-mcp/watch"><img src="https://agentmods.dev/badge/skills/ino-xious/stockbit-mcp/watch/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/watch"><img src="https://agentmods.dev/badge/skills/ino-xious/stockbit-mcp/watch.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 analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
- medium MCP Rug Pull · line 60 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00088 | $0.02561 |
| Opus 5 | $0.00044 | $0.01281 |
| Sonnet 5 | $0.00018 | $0.00512 |
| Haiku 4.5 | $0.00009 | $0.00256 |
Grade A, and why
watch 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 10d 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Watch live IDX turnover
/watch <stocks|watchlist|all> <time-frame> <prompt>
/watch BBCA,ANTM 30s is anyone dumping
/watch watchlist 1m what is moving
/watch watchlist:Bandar 30s any unusual size
/watch all 5m where is the money going
What this actually does — read before answering
It takes two readings of the market some seconds apart and reports the difference. That is the whole mechanism. Δvalue / Δfrequency is the average rupiah size of the prints that landed in the window.
It does not watch continuously. One command, one window, one answer. Nothing runs afterwards, nothing will notify the user later. If they ask to be told when something happens, say plainly that this samples on demand and a background watcher does not exist yet.
It does not judge whether anything was big. No threshold is defined — see The cutoff question below, which is not optional.
Step 1 — read the arguments
They arrive as $ARGUMENTS (individually as $1, $2, …). If nothing was substituted, take them from the user's message after /watch.
| position | meaning | accepted |
|---|---|---|
| 1 — scope, required | what to look at | BBCA · BBCA,ANTM · watchlist · watchlist:Name · all |
| 2 — interval, optional | how long a window to measure | 20s · 30s · 1m · 5m · realtime (also menit / detik) |
| 3+ — prompt, optional | the question, in the user's own words, either language | anything |
Only the scope is required. Fill in the rest rather than refusing — a public user typing /watch BBCA should get an answer, not a usage error:
- No interval given → use
30s. Do not use the parser's own 5-minute default here: five minutes means the command blocks for five minutes. Only use a long window when the user actually asked for one. - No prompt given → report what traded, ranked, and stop. No question to answer is not an error.
- Nothing at all given → default to
all 30sand describe the most active names. Do not ask a clarifying question first; run it, then mention the fuller form.
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.
- 10d ago First seen · 160 lines · 88 tokens per session scan A f23074d89164
watch is a skill published in the GitHub repository INo-xious/stockbit-mcp (29 stars, last pushed yesterday), licensed MIT. It adds 88 tokens to every session and 2,561 once invoked, about $0.0004 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
chief-financial-officer
Owns the financial position: planning, budgeting, forecasting, unit economics, cash, and the numbers the business is run and reported on. Use this to build or challenge a budget, model a decision's financial consequence, assess unit economics or runway, evaluate an investment or spend request, set financial controls…
fundraising-and-investor-relations
Raises capital and manages the relationship afterward — deciding how much and why, understanding what dilution and preferences actually cost, running a process with real competitive tension, preparing for diligence before it starts, and reporting to investors and a board in a way that keeps support when results are…
cost-accounting
Establishes what something actually costs — fixed, variable and mixed cost behavior, absorption versus variable costing, job-order, process and activity-based methods, breakeven and operating leverage, and price/volume/mix decomposition. Use this to set a price floor, explain why revenue or margin moved, decide make…
financial-statement-analysis
Reads a set of financial statements and establishes what changed and why — fluctuation analysis against prior period and against budget, profitability, liquidity, solvency and efficiency ratios, benchmarking, and the non-GAAP measures presented alongside them. Use this to interpret results, review a counterparty's or…
internal-controls-and-audit
Designs and tests controls over financial reporting — segregation of duties, approval limits, evidence, and preparing for audit. Use this to design controls for a process, prepare for an external audit, respond to an audit finding, set approval thresholds, or assess where a small team's segregation of duties is…
payroll-operations
Runs the pay cycle so it is right, on time, and provable — the calendar and cutoffs, what feeds pay from the HRIS and time systems, gross-to-net and the deductions in it, multi-jurisdiction registration and tax filing, off-cycle payments and corrections, and the reconciliation to the general ledger. Use this to design…