agentmods.dev

heurist-finance: Skill for Claude Code

.claude/skills/stock-screener/SKILL.md

stock-screener is a skill for Claude Code from heurist-network/heurist-finance. It costs 81 tokens per session (1,214 once invoked), scanned A, original, MIT.

A stock-screening method that starts with a specific explanation for why a group of companies may be mispriced, then filters candidates through business-quality and trading-risk checks. Mispriced means the market price may not reflect a company's likely value.

In plain words
What is it for?
Use it to find stocks matching value, growth, momentum, or short-selling ideas, while stating who may be overlooking them and what could change the market's view.
Why use it?
It prevents a stock screen from becoming an unexplained list of companies that match superficial numbers. The hypothesis makes clear what the screen is looking for and what might cause the price difference to close.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is heurist-network/heurist-finance's own configuration. It tells Claude Code how to work on heurist-finance itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything heurist-finance configures →

not rated 11repo 14d ago A scan 81 tokens original MIT
View source ↗ heurist-network/heurist-finance finance.heurist.ai
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/stock-screener/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.

agentmods badge for stock-screener

README.md
[![agentmods](https://agentmods.dev/badge/skills/heurist-network/heurist-finance/stock-screener/github.svg)](https://agentmods.dev/skills/heurist-network/heurist-finance/stock-screener)
Your own site
<a href="https://agentmods.dev/skills/heurist-network/heurist-finance/stock-screener"><img src="https://agentmods.dev/badge/skills/heurist-network/heurist-finance/stock-screener/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.

agentmods 80×15 button for stock-screener

Your own site · 80×15
<a href="https://agentmods.dev/skills/heurist-network/heurist-finance/stock-screener"><img src="https://agentmods.dev/badge/skills/heurist-network/heurist-finance/stock-screener.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,214 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00081 $0.01214
Opus 5.5 $0.00032 $0.00486
Sonnet 5.5 $0.00016 $0.00243
Haiku 4.5 $0.00008 $0.00121

Measured 13d ago against content hash 831ca1dd2640, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

stock-screener 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/stock-screener/SKILL.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stock Screener

Shared plumbing and output contract: ../_shared/analyst-core.md. A screen is a hypothesis about why a group of stocks is systematically mispriced, executed as a filter. A screen without that hypothesis is a list — and the failure mode of all public screening content — because every popular filter's output is visible to everyone running the same screener, so the raw list itself carries no edge. The edge is in the hypothesis + the funnel behind the list.

Step 1 — Name the hypothesis (before touching a screener)

Force the one-sentence form: "These stocks are cheap/misjudged because [mechanism], and the seller/avoider is [who], so the mispricing closes when [what]." Examples that qualify:

  • "Profitable small caps with insider-buying clusters are under-covered because no institution can size them; closes as results force coverage." (→ small-cap-scout + event-driven gates)
  • "Post-guidance-raise names drift because analysts update in steps." (→ earnings-play PEAD funnel)
  • "Cheap cyclicals near capitulation are avoided because last cycle's losses are recent memory; closes on the cycle turn." (→ valuation-expectations mid-cycle math)
  • "High-FCF-yield + improving F-Score value names are lumped with value traps; the quality split is the edge." (Piotroski's actual finding — the combination is the screen)

If the user can't name the mechanism, help construct it — or say plainly the screen is a list, not an edge, and what would make it one.

Step 2 — Execute (curated screens + SQL-style discipline)

yahoo equity_screen offers the curated set (describe for the enum): undervalued_large_caps, undervalued_growth_stocks, growth_technology_stocks, small_cap_gainers, aggressive_small_caps, most_shorted_stocks, day_gainers/losers, most_actives. These are candidate feeds, not answers — map the hypothesis to the nearest feed(s), pull generously (limit=25), and treat the day-based screens as flow/attention samplers rather than idea sources. For hypotheses the curated screens can't express, build the universe from other angles: sector ETF holdings (fund_snapshot), tickers named in theme news (yahoo news_search, web), insider-cluster names (insider_activity), and screen those with per-name pulls.

Read the full file on GitHub · 43 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.

  1. 13d ago First seen · 43 lines · 81 tokens per session scan A 831ca1dd2640

Subscribe to this mod's changes

stock-screener is a skill published in the GitHub repository heurist-network/heurist-finance (11 stars, last pushed 14d ago), licensed MIT. It adds 81 tokens to every session and 1,214 once invoked, about $0.0003 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 fintechai-agentscodex
Related

stock-screener compared with skills from other repositories

stock-screener next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
stock-screenerheurist-network/heurist-financeSkill1114d agoMITA81Claude Code
sector-rotationHKUDS/Vibe-TradingSkill38kyesterdayMITA39Claude Code, Codex
twitter-readerhimself65/finance-skillsSkill3.5k2d agoMITA110Claude Code
strategy-pivot-designertradermonty/claude-trading-skillsSkill3.7k2d agoMITA28Claude Code, Codex
energy-procurementhashgraph-online/awesome-codex-pluginsSkill1.5kyesterdayApache-2.0A93Claude Code, Codex
airdrop-hunting-guidenirholas/three.wsSkill269yesterdayApache-2.0A54Claude Code, Codex
multi-expert-analyzerdigoal/blogSkill8.6k2d agoGPL-2.0A292Codex