clawby-data

clawby-data is a skill for Claude Code, Codex from openclawby/openclawby-skills. It costs 215 tokens per session (4,618 once invoked), scanned A, original, MIT.

A set of instructions for retrieving and analyzing current financial data through the Clawby data API. It covers data such as prices, trading activity, options, crypto, foreign exchange, company financial reports, and regulatory filings.

In plain words
What is it for?
Use it to investigate assets and markets, compare financial information, examine company filings, or analyze trading and market data. It requires a Clawby API key and the relevant API catalogue entry.
Why use it?
It provides a defined process for finding the right data interface and gathering information from more than one available source before analyzing it.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: mentions Claude Code; mentions Codex; built for openclaw.

Good fit Use it to investigate assets and markets, compare financial information, examine company filings, or analyze trading and market data. It requires a Clawby API key and the relevant API catalogue entry.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/openclawby/openclawby-skills/clawby-data
Install

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.

Any agent
npx skills add openclawby/openclawby-skills --skill clawby-data
Clone the repo
git clone --depth 1 https://github.com/openclawby/openclawby-skills

Made for: Claude Code, Codex.

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 clawby-data

README.md
[![agentmods](https://agentmods.dev/badge/skills/openclawby/openclawby-skills/clawby-data/github.svg)](https://agentmods.dev/skills/openclawby/openclawby-skills/clawby-data)
Your own site
<a href="https://agentmods.dev/skills/openclawby/openclawby-skills/clawby-data"><img src="https://agentmods.dev/badge/skills/openclawby/openclawby-skills/clawby-data/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 clawby-data

Your own site · 80×15
<a href="https://agentmods.dev/skills/openclawby/openclawby-skills/clawby-data"><img src="https://agentmods.dev/badge/skills/openclawby/openclawby-skills/clawby-data.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 215 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,618 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00215 $0.04618
Opus 5 $0.00108 $0.02309
Sonnet 5 $0.00043 $0.00924
Haiku 4.5 $0.00021 $0.00462

Measured 10d ago against content hash 0b0b1c8e0e5f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

clawby-data scanned grade A with 1 finding 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 10d ago.

The scan reads SKILL.md. This mod also ships 6 executable files (akdata/_akcall.py, akdata/_akenv.py, akdata/_akindex.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

**Works with any AI agent** — Claude Code, Codex, OpenClaw, Hermes, and anything that can run shell commands or call an HTTP API: just an API key + the catalog + plain `curl`.
clawby-data/SKILL.md · 215 lines

How it starts

The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Clawby Data Analysis

Fetch real financial data through the Clawby aggregated data API and analyze it. The single source of truth for every interface — its params (required · format · example) and ⚠️ pitfalls — is api/catalog/ (start at api/catalog/_index.yaml). Always read the relevant category yaml before calling. The full machine catalog is api/clawby.yaml (server-generated, versioned).

Works with any AI agent — Claude Code, Codex, OpenClaw, Hermes, and anything that can run shell commands or call an HTTP API: just an API key + the catalog + plain curl.

Quick start

# 1. Auth (once): sign in at https://www.openclawby.com/ → export CLAWBY_API_KEY=pk_xxx
# 2. Find the interface in api/catalog/<category>/  (routing table below)
# 3. Call it:
curl -s -X POST https://api.openclawby.com/api/relay \
  -H "X-API-Key: $CLAWBY_API_KEY" -H "Content-Type: application/json" \
  -d '{"name":"<interface name from catalog>","params":{ ... }}'
# → {source, data, credits:{remaining,used_total}}

Core workflow · Gather ALL available data first, then analyze

Completeness is the goal. A thin answer from a single source is a failure even when correct — go broad first, analyze second. Apply this to every request.

  1. Turn the request into a data checklist. Ask "what would a thorough analyst pull?" and list every relevant dimension. Over-collect on purpose (a stock → quote, short data, dark pool, options, financials, sentiment, peers; a token → DEX price/liquidity, holders, funding & OI, odds, social buzz).
  2. For each item, sweep ALL FOUR source layers — never stop at the first hit:
    • Layer 1 — Clawby data (/api/relay + on-chain /api/rpc): scan the catalog for every interface that touches the item and call them all. Primary, authoritative.
    • Layer 2 — Local akshare (akdata/, read-only): China markets (A-shares · HK · futures · convertible bonds · ETFs · boards · northbound flows · dragon-tiger list · shareholder data) and global macro (CPI · non-farm · PMI · rate decisions) — 1080 interfaces Layer 1 does not carry. Runs locally on the user's machine with no Clawby key and no credits. Guide: akdata/akshare.md.
    • Layer 3 — Execution connectors (exec/, read-only use): the Binance / Bitget / OKX / Polymarket CLIs expose market data, order books, funding, smart-money and news the other layers may not have. Read-only needs no confirmation.
    • Layer 4 — Your own web access: news, filings, official docs, macro context — fill every remaining gap.
  3. Maximize coverage. If two layers supply the same metric, fetch both and cross-check. Fire independent fetches in parallel. Never skip a reachable source.
  4. Track coverage, then analyze. Ground every claim in collected data; if a source failed, say so instead of silently dropping the dimension.
  5. Offer a formal report when it fits — for substantial asset analysis, offer a professional PDF research report (see Professional analysis reports). Ask first.

Read the full file on GitHub · 215 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 10d ago First seen · 215 lines · 215 tokens per session scan A 0b0b1c8e0e5f

Subscribe to this mod's changes

clawby-data is a skill published in the GitHub repository openclawby/openclawby-skills (9 stars, last pushed 1mo ago), licensed MIT. It adds 215 tokens to every session and 4,618 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

fundraising-and-investor-relations

Raises capital and manages the relationship afterward — deciding how much and why, understanding what dilution and preferences actually cost, running a process with real competitive tension, preparing for diligence before it starts, and reporting to investors and a board in a way that keeps support when results are…

cbrock84/headcount · 91 tokens

chief-financial-officer

Owns the financial position: planning, budgeting, forecasting, unit economics, cash, and the numbers the business is run and reported on. Use this to build or challenge a budget, model a decision's financial consequence, assess unit economics or runway, evaluate an investment or spend request, set financial controls…

cbrock84/headcount · 88 tokens

internal-controls-and-audit

Designs and tests controls over financial reporting — segregation of duties, approval limits, evidence, and preparing for audit. Use this to design controls for a process, prepare for an external audit, respond to an audit finding, set approval thresholds, or assess where a small team's segregation of duties is…

cbrock84/headcount · 67 tokens

sales-compensation-and-territory

Designs quotas, territories and commission plans that produce the behavior the business needs — sizing territories against real potential, setting quotas people can hit often enough to believe in, choosing what to pay on, handling accelerators, draws, clawbacks and disputes, and changing a plan without destroying…

cbrock84/headcount · 96 tokens

capital-structure-and-covenants

Decides how the business is financed and what that financing then requires of it — debt versus equity, weighted average cost of capital as a hurdle rate, how much leverage cash flow can carry, and the financial, affirmative and negative covenants, definitions, test dates and cure rights that come attached. Use this to…

cbrock84/headcount · 102 tokens

cost-accounting

Establishes what something actually costs — fixed, variable and mixed cost behavior, absorption versus variable costing, job-order, process and activity-based methods, breakeven and operating leverage, and price/volume/mix decomposition. Use this to set a price floor, explain why revenue or margin moved, decide make…

cbrock84/headcount · 92 tokens