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/skills/wrds-schema/SKILL.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/skills/alexander-m-dickerson/ai-asset-pricing/wrds-schema)<a href="https://agentmods.dev/skills/alexander-m-dickerson/ai-asset-pricing/wrds-schema"><img src="https://agentmods.dev/badge/skills/alexander-m-dickerson/ai-asset-pricing/wrds-schema/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/alexander-m-dickerson/ai-asset-pricing/wrds-schema"><img src="https://agentmods.dev/badge/skills/alexander-m-dickerson/ai-asset-pricing/wrds-schema.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 | $0.00090 | $0.01964 |
| Opus 5 | $0.00045 | $0.00982 |
| Sonnet 5 | $0.00018 | $0.00393 |
| Haiku 4.5 | $0.00009 | $0.00196 |
Grade A, and why
wrds-schema 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.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WRDS Schema Pre-loader
You are starting a session that involves WRDS PostgreSQL queries. Before writing any queries, load the schema knowledge you need by dispatching specialist agents in parallel.
Examples
/wrds-schema crsp-- load CRSP schema only/wrds-schema crsp optionm-- load CRSP + OptionMetrics schemas/wrds-schema all-- load all available schemas
Connection
Connection details are in ~/.pg_service.conf; password in ~/.pgpass.
psql service=wrds
For Python, use psycopg2.connect("service=wrds"). Do NOT use pd.read_sql (broken with psycopg2 on Python 3.13) — use cursors directly and cast Decimal to float.
Prerequisite: The specialist agents (crsp-wrds-expert, optionmetrics-wrds-expert, taq-wrds-expert) must have Bash in their tools: frontmatter in ~/.claude/agents/. Without it, they cannot run psql queries.
What to do
Based on $ARGUMENTS (or "all" if none given), launch the appropriate specialist agents in parallel using the Task tool. Each agent should query the WRDS database to retrieve current schema details and return a concise reference.
Agent dispatches
For each requested database, launch a Task with subagent_type set to the matching specialist:
| Keyword | Agent | Task |
|---|---|---|
crsp |
crsp-wrds-expert |
Retrieve schema for crsp.dsf, crsp.dsi, crsp.msf, crsp.msi, crsp.stocknames, delisting tables. Confirm column names (date not caldt), PERMNO lookup for SPY (84398), index columns in dsi (spindx, sprtrn). Note Decimal type from psycopg2. |
optionm |
optionmetrics-wrds-expert |
Retrieve schema for optionm.opprcd{YYYY} (yearly partitioned), optionm.securd, optionm.zerocd. Confirm: strike_price is strike*1000, SPX SECID=108105, SPY SECID=109820, XSP SECID=189691. Column names for options tables. LEAPS expiry cycles (Jun/Dec for 2Y). |
comp |
crsp-wrds-expert |
Retrieve Compustat comp.funda/comp.fundq key columns, standard filters (INDL/STD/D/C), CCM linking via crsp.ccmxpf_lnkhist (columns, linktype LC/LU, linkprim P/C, deduplication pattern). |
taq |
taq-wrds-expert |
Retrieve TAQ table structure, trade filtering rules (TR_CORR, TR_SCOND), NBBO tables. Note: TAQ requires SAS on WRDS, not SQL. |
jkp |
crsp-wrds-expert |
Load Global Factor Data schema: contrib.global_factor key columns (permno, gvkey, eom, excntry, me, ret_exc, be_me, etc.), standard filters (excntry='USA', obs_main=1, common=1, exch_main=1, primary_sec=1), column categories, performance rules (always filter excntry + date range). 443 cols, 30M+ rows. |
bonds |
bonds-wrds-expert |
Load Dickerson corporate bond schema: monthly (contrib.dickerson_bonds_monthly, 140 cols, 2.7M rows) and daily (contrib.dickerson_bonds_daily, 43 cols, 30M rows). Rating encoding (1-22), return measures, spread/duration metrics, identifier linkage to CRSP/Compustat (84%). Column names differ between tables. |
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 · 96 lines · 90 tokens per session scan A 859e4bca0e1e
wrds-schema is a skill published in the GitHub repository Alexander-M-Dickerson/ai-asset-pricing (59 stars, last pushed 4mo ago), licensed MIT. It adds 90 tokens to every session and 1,964 once invoked, about $0.0005 per session on Opus 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.
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.