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 ferinator/bullrun-mcp --skill company-deep-divegit clone --depth 1 https://github.com/ferinator/bullrun-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/ferinator/bullrun-mcp/company-deep-dive)<a href="https://agentmods.dev/skills/ferinator/bullrun-mcp/company-deep-dive"><img src="https://agentmods.dev/badge/skills/ferinator/bullrun-mcp/company-deep-dive/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/ferinator/bullrun-mcp/company-deep-dive"><img src="https://agentmods.dev/badge/skills/ferinator/bullrun-mcp/company-deep-dive.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 | $0.00101 | $0.01618 |
| Opus 5.5 | $0.00040 | $0.00647 |
| Sonnet 5.5 | $0.00020 | $0.00324 |
| Haiku 4.5 | $0.00010 | $0.00162 |
Grade A, and why
company-deep-dive 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 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.
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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Company deep dive
This skill uses the Bullrun connector to research one company. It ends in a dated summary that says which data it is based on and which data is missing. It describes the company; it doesn't make a buy or sell call.
Ground rules
- Date everything. Each figure carries its own date: the price date, the fiscal period, when a risk score was computed, when a news article was published. Never present stored data as live.
- Native currency. Prices are in the listing's trading currency. Financials are in the company's reporting currency (
sourceCurrency). Don't convert silently. GBX (pence) and GBP are different units. - Missing means unknown. An empty dataset, a null field, a dark risk dial or no relationship edges means Bullrun has no data. It does not mean zero risk, no news or no suppliers.
- Bullrun's own scores are descriptive. The valuation gap compares the current multiple with what similar companies typically command. It is not a price target. Risk bands (Contained, Normal, Elevated, Stretched, Acute) describe measured strain. Neither is a buy or sell view.
- Reuse results. Don't re-fetch what you already have. The free connection includes 700 successful tool calls per rolling 30 days, shared by anonymous network. Each successful call counts once; failed calls use no allowance. If a temporary capacity or pacing limit asks you to wait, follow its retry guidance.
Steps
1. Resolve the listing
If the user gave a company name, an ISIN or an ambiguous symbol, call search_stocks with query. It returns candidate listings and never picks one when alternatives remain. If several listings or share classes match, show them (exchange, currency, ticker) and ask which one, or use the home-market listing when the user's wording makes that clear. Bullrun tickers are the plain local symbol for US and most European listings (AAPL, ASML, NESN) and keep the exchange suffix for most Asian ones (6324.T, 0700.HK).
2. Check what Bullrun has before going deep
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 Changed b650030bfe02
- 15d ago First seen · 76 lines · 101 tokens per session scan A a2f263a7fbef
company-deep-dive is a skill published in the GitHub repository ferinator/bullrun-mcp (0 stars, last pushed 8d ago), licensed MIT. It adds 101 tokens to every session and 1,618 once invoked, about $0.0004 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 2026-10-22.
company-deep-dive compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| company-deep-diveferinator/bullrun-mcp | Skill | 0 | 8d ago | MIT | A | 101 | Claude Code |
| defeatbeta-earnings-analysisdefeat-beta/defeatbeta-api | Skill | 795 | 7d ago | Apache-2.0 | A | 112 | Claude Code |
| tickdb-market-dataTickDB/tickdb-unified-realtime-marketdata-api | Skill | 915 | 23d ago | MIT | A | 165 | Claude Code, Codex |
| defeatbeta-earnings-previewdefeat-beta/defeatbeta-api | Skill | 795 | 7d ago | Apache-2.0 | A | 60 | Claude Code, Codex |
| sprrwilsonfreitas/awesome-quant | Skill | 30k | yesterday | none | A | 60 | Claude Code, Codex |
| defeatbeta-earnings-key-datadefeat-beta/defeatbeta-api | Skill | 795 | 7d ago | Apache-2.0 | A | 138 | Claude Code, Codex |
| create-entrywilsonfreitas/awesome-quant | Skill | 30k | yesterday | none | A | 43 | Claude Code, Codex |