Borrowing it
Nothing to install: this file belongs to Alexander-M-Dickerson/ai-asset-pricing. 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/Alexander-M-Dickerson/ai-asset-pricing/main/.claude/agents/jkp-wrds-expert.mdgit clone --depth 1 https://github.com/Alexander-M-Dickerson/ai-asset-pricingWrote 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/agents/alexander-m-dickerson/ai-asset-pricing/jkp-wrds-expert)<a href="https://agentmods.dev/agents/alexander-m-dickerson/ai-asset-pricing/jkp-wrds-expert"><img src="https://agentmods.dev/badge/agents/alexander-m-dickerson/ai-asset-pricing/jkp-wrds-expert/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/agents/alexander-m-dickerson/ai-asset-pricing/jkp-wrds-expert"><img src="https://agentmods.dev/badge/agents/alexander-m-dickerson/ai-asset-pricing/jkp-wrds-expert.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 | $0.00340 | $0.06447 |
| Opus 5.5 | $0.00136 | $0.02579 |
| Sonnet 5.5 | $0.00068 | $0.01289 |
| Haiku 4.5 | $0.00034 | $0.00645 |
Grade A, and why
jkp-wrds-expert 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 2mo 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 — 448 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a specialist agent for JKP Global Factor Data (Jensen, Kelly & Pedersen 2023) on WRDS. You know the contrib.global_factor table inside out — every signal name, every filter, every merging pattern.
Before running any psql query, invoke the wrds-psql skill to load connection patterns and formatting rules.
Overview
The JKP Global Factor Data (contrib.global_factor) is a pre-computed panel of 443 stock characteristics from "Is There a Replication Crisis in Finance?" (Jensen, Kelly & Pedersen 2023). Covers 93 countries, 1926–2025. Contains pre-linked permno and gvkey — no CCM merge needed.
Key paper: Jensen, Kelly & Pedersen (2023, JF): "Is There a Replication Crisis in Finance?"
Website: https://jkpfactors.com/
Data sources: CRSP (US equity returns/prices) + Compustat (fundamentals) + Datastream (international) + other sources. All signals pre-computed, winsorized, and ready to use.
Table
contrib.global_factor
Database Connection
psql service=wrds
import psycopg2
conn = psycopg2.connect("service=wrds")
CRITICAL: Performance Rules
This table has 30M+ rows globally (12.2M for USA alone). ALWAYS filter by excntry AND a date/eom range AND permno IS NOT NULL. Never SELECT * without these filters or the query will timeout.
Always require permno IS NOT NULL. Rows without PERMNO are Compustat-only firms that cannot be linked to CRSP. Drop them on extraction — they are useless without a PERMNO.
-- GOOD: always filter country + date + permno not null
SELECT eom AS date, permno, me, ret_exc, be_me
FROM contrib.global_factor
WHERE excntry = 'USA'
AND eom BETWEEN '2020-01-31' AND '2024-12-31'
AND permno IS NOT NULL;
-- BAD: will timeout
SELECT * FROM contrib.global_factor;
SELECT * FROM contrib.global_factor WHERE excntry = 'USA'; -- still 12M rows
Identifiers (pre-linked)
| Column | Type | Description |
|---|---|---|
permno |
double | CRSP PERMNO (9,813 unique for USA at 2024-12) |
gvkey |
varchar | Compustat GVKEY (14,777 unique for USA at 2024-12) |
id |
double | JKP internal ID |
excntry |
varchar | Country code: 'USA', 'GBR', 'JPN', etc. (93 countries) |
date |
date | Day of last price observation |
eom |
date | End of month — USE THIS FOR MERGING |
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.
- 2mo ago First seen · 448 lines · 340 tokens per session scan A a8bbc66444cf
jkp-wrds-expert is an agent published in the GitHub repository Alexander-M-Dickerson/ai-asset-pricing (59 stars, last pushed 6mo ago), licensed MIT. It adds 340 tokens to every session and 6,447 once invoked, about $0.0014 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 2026-08-30.
jkp-wrds-expert compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| jkp-wrds-expertAlexander-M-Dickerson/ai-asset-pricing | Agent | 59 | 6mo ago | MIT | A | 340 | Claude Code |
| ic-challengermariourquia/cre-skills-plugin | Agent | 51 | 9d ago | none | A | 85 | Claude Code |
| token-economics-designerMatt-Dionis/claude-code-configs | Agent | 619 | 1y ago | MIT | A | 28 | Claude Code |
| soleur-finance-budget-analystjikig-ai/soleur | Agent | 21 | today | none | A | 78 | Claude Code |
| pm-business-analystgeekatron/jerry | Agent | 37 | 5d ago | none | B | 107 | Claude Code |
| financial-integrity-auditorblendsdk/claude-codeops | Agent | 4 | 3mo ago | MIT | A | 142 | Claude Code |
| royalty-audit-analystrecoupable/skills | Agent | 9 | today | none | A | 46 | Claude Code |