A market-research workflow gathers prices, economic data, company filings, options information, and web sources through one command-line tool. It can support research on a ticker, event, trade idea, or broader market question and combine findings from multiple sources.

Use it to research companies, market events, economic conditions, options, filings, and trade theses, including research that needs several data sources and cited findings.

Market data tools often have inconsistent inputs and output formats, and manually combining sources makes research slower and more error-prone. This provides a repeatable way to fetch and organise the information needed for an analysis.

How heurist-network/heurist-finance configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to heurist-network/heurist-finance. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/heurist-network/heurist-finance/main/.claude/skills/hf-research/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/heurist-network/heurist-finance

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/heurist-network/heurist-finance/hf-research/github.svg)](https://agentmods.dev/skills/heurist-network/heurist-finance/hf-research)

Your own site

<a href="https://agentmods.dev/skills/heurist-network/heurist-finance/hf-research"><img src="https://agentmods.dev/badge/skills/heurist-network/heurist-finance/hf-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/heurist-network/heurist-finance/hf-research"><img src="https://agentmods.dev/badge/skills/heurist-network/heurist-finance/hf-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,790 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00102	$0.01790
Opus 5.5	$0.00041	$0.00716
Sonnet 5.5	$0.00020	$0.00358
Haiku 4.5	$0.00010	$0.00179

Measured 13d ago against content hash 56b2e5b06fa6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

hf-research 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 13d 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.

.claude/skills/hf-research/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

HF Research

Overview

Two layers:

scripts/hf_tool.py — a deterministic data-fetch CLI. Everything we reach for during research (Mesh tools, prices, options, earnings, FRED, Exa web) behind one terse, JSON-out interface. Callable directly and by subagents via Bash.
This skill's subagent recipe — how to fan the CLI + Claude-native WebSearch across parallel subagents and synthesize a cited answer.

The CLI exists because raw Mesh calls are error-prone: param names vary (series_key, search_term, symbols), responses are double-enveloped, and price_history silently caps at 250 bars. The CLI handles all of that. Prefer it over hand-writing uv run python -c "from src.clients.mesh import ...".

The data CLI

Run from repo root (no PYTHONPATH needed — the script inserts it). Output is JSON to stdout; add --out FILE to write to a file instead (do this for big price pulls to keep them out of context).

Command	What it does
`hf_tool.py tools [agent]`	list Mesh tool names (`agent` ∈ yahoo, fred, sec, exa)
`hf_tool.py describe <agent> <tool>`	dump a tool's params, required list, and enum values — do this first instead of guessing param names
`hf_tool.py call <agent> <tool> k=v ...`	invoke any Mesh tool, auto-unwrapped. Values are JSON-coerced; `k=a,b` → list. Use `--json '{...}'` for full control
`hf_tool.py prices SYM... [--period 1y\| --start --end] [--full]`	daily bars with automatic 250-bar pagination (stitches 6-mo chunks). Default = closes only; `--full` = OHLCV
`hf_tool.py web "query" [--n 5]`	Exa web search (deterministic)

# discover, then call — the two-step that avoids param errors
uv run python scripts/hf_tool.py describe fred macro_series_history
uv run python scripts/hf_tool.py call fred macro_series_history series_key=ust_10y view=change limit=60
# prices for a backtest, dumped to a file
uv run python scripts/hf_tool.py prices AAPL MSFT CRM SPY --period 5y --out /tmp/px.json

Read the full file on GitHub · 73 lines

Changes

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.

13d ago First seen · 73 lines · 102 tokens per session scan A 56b2e5b06fa6

Subscribe to this mod's changes

hf-research is a skill published in the GitHub repository heurist-network/heurist-finance (11 stars, last pushed 14d ago), licensed MIT. It adds 102 tokens to every session and 1,790 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 2026-10-24.

Finance and fintech Research ai-agents codex

hf-research next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
hf-researchheurist-network/heurist-finance	Skill	11	14d ago	MIT	A	102	Claude Code
sector-rotationHKUDS/Vibe-Trading	Skill	38k	yesterday	MIT	A	39	Claude Code, Codex
twitter-readerhimself65/finance-skills	Skill	3.5k	2d ago	MIT	A	110	Claude Code
strategy-pivot-designertradermonty/claude-trading-skills	Skill	3.7k	2d ago	MIT	A	28	Claude Code, Codex
energy-procurementhashgraph-online/awesome-codex-plugins	Skill	1.5k	yesterday	Apache-2.0	A	93	Claude Code, Codex
airdrop-hunting-guidenirholas/three.ws	Skill	269	yesterday	Apache-2.0	A	54	Claude Code, Codex
multi-expert-analyzerdigoal/blog	Skill	8.6k	2d ago	GPL-2.0	A	292	Codex

heurist-finance: Skill for Claude Code