Borrowing it
Nothing to install: this file belongs to GlacianNex/fmp-qualtrim-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/GlacianNex/fmp-qualtrim-mcp/main/.claude/skills/stock-research/SKILL.mdgit clone --depth 1 https://github.com/GlacianNex/fmp-qualtrim-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/glaciannex/fmp-qualtrim-mcp/stock-research)<a href="https://agentmods.dev/skills/glaciannex/fmp-qualtrim-mcp/stock-research"><img src="https://agentmods.dev/badge/skills/glaciannex/fmp-qualtrim-mcp/stock-research/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/glaciannex/fmp-qualtrim-mcp/stock-research"><img src="https://agentmods.dev/badge/skills/glaciannex/fmp-qualtrim-mcp/stock-research.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00120 | $0.03702 |
| Opus 5 | $0.00060 | $0.01851 |
| Sonnet 5 | $0.00024 | $0.00740 |
| Haiku 4.5 | $0.00012 | $0.00370 |
Grade B, and why
stock-research scanned grade B with 1 finding 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 11d 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
so never tell the user a question cannot be answered because Qualtrim is How it starts
The opening of the file, as written. The whole thing — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
stockdata MCP server
Everything needed to use this server well: what it is, which backend answers what, how much you may call, what must not be touched, and how failures read.
What it is
An MCP server exposing 55 tools over two backends: Financial Modeling Prep (required) and Qualtrim (optional).
Qualtrim is optional and often absent. When its credentials are not set, the 22
qualtrim_* tools are not registered at all and the other 33 work normally —
so never tell the user a question cannot be answered because Qualtrim is
missing. Answer it from FMP, which holds the raw data either way.
FMP (fmp_*, 29 tools) |
Qualtrim (qualtrim_*, 22 tools) |
|
|---|---|---|
| What | Financial Modeling Prep, a documented public API | Qualtrim's private API, read off their shipped web bundle |
| Holds | Raw data — statements, quotes, ratios, estimates, prices, dividends | A derived layer built on FMP, plus the user's own holdings |
| Auth | API key | Session cookie from the user's paid account |
| Budget | ~250 requests/day on the free key | Interactive volumes only — a social limit, not a quota |
| Stability | Versioned, documented | None; routes change without notice |
| Cost of abuse | Rate-limit error | The user's paid account can be terminated |
Qualtrim is an FMP customer. It buys the same raw data and adds a layer on top. So every plain financial number Qualtrim returns is also available from FMP — through a slower, more fragile, more consequential path.
Rule: FMP by default. Qualtrim only for what Qualtrim itself computes, or when the user's own portfolio or watchlist is the subject.
backend_status reports which backends are configured and whether writes are
enabled. Call it when a qualtrim_* tool is missing or behaving oddly.
Configuration
Set by the operator, not adjustable at runtime. Useful for explaining failures.
| Variable | Default | Effect |
|---|---|---|
FMP_API_KEY |
— | Without it, every fmp_* tool errors |
QUALTRIM_USERNAME / QUALTRIM_PASSWORD |
— | Absent means the 22 qualtrim_* tools are not registered at all |
QUALTRIM_ENABLE_WRITES |
false |
The two write tools refuse to run while false |
QUALTRIM_MIN_INTERVAL |
1.0 |
Seconds between Qualtrim requests |
FMP_MIN_INTERVAL |
0.1 |
Seconds between FMP requests |
MAX_RESPONSE_CHARS |
50000 |
Oversized payloads are trimmed with a truncation note — narrow the request rather than re-calling |
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.
- 11d ago First seen · 280 lines · 120 tokens per session scan B ce688c6e74ca
stock-research is a skill published in the GitHub repository GlacianNex/fmp-qualtrim-mcp (0 stars, last pushed 17d ago), licensed MIT. It adds 120 tokens to every session and 3,702 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (subtle steering). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
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…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
furusato
A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.
reading-receipt
An image-reading workflow for extracting structured information from receipts, invoices, and hometown-tax donation certificates. It can first extract text from PDFs and otherwise read their images.