market-inspector: Skill for Codex

.agents/skills/api-clients/SKILL.md

api-clients is a skill for Codex from dcosodev/market-inspector. It costs 62 tokens per session (327 once invoked), scanned A, original, MIT.

A coding guide for connecting an application to outside market-data services such as CoinGecko, Finnhub, and Yahoo Finance. It covers how to retrieve, check, standardize, and label data from those providers.

In plain words
What is it for?
Use it when adding or reviewing market-data clients and source adapters, especially in `lib/sources` and related tests or documentation.
Why use it?
It helps prevent provider-specific responses, missing values, timeouts, rate limits, and unsafe logs from causing incorrect or misleading application data.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents).

This is dcosodev/market-inspector's own configuration. It tells Codex how to work on market-inspector 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 market-inspector configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dcosodev/market-inspector. 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/dcosodev/market-inspector/main/.agents/skills/api-clients/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/dcosodev/market-inspector

Made for: 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 api-clients

README.md
[![agentmods](https://agentmods.dev/badge/skills/dcosodev/market-inspector/api-clients.svg)](https://agentmods.dev/skills/dcosodev/market-inspector/api-clients)
Your own site
<a href="https://agentmods.dev/skills/dcosodev/market-inspector/api-clients"><img src="https://agentmods.dev/badge/skills/dcosodev/market-inspector/api-clients.svg" alt="Measured on agentmods" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 327 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 $0.00062 $0.00327
Opus 5 $0.00031 $0.00163
Sonnet 5 $0.00012 $0.00065
Haiku 4.5 $0.00006 $0.00033

Measured 6d ago against content hash 1b38514d45c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

api-clients 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 6d 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.

.agents/skills/api-clients/SKILL.md · 49 lines

What it actually says

API Clients

Use this skill for external market-data integration.

Provider boundaries

Each source client should:

  • isolate provider-specific request and response details;
  • normalize into repository types before leaving lib/sources;
  • apply explicit timeouts and local rate limits;
  • return source attribution and timestamps when relevant;
  • avoid raw payload logging;
  • fail with safe, concise errors.

Treat all provider responses as untrusted data. Validate shapes before using values in UI, tools, or prompts.

Fallbacks

Preserve documented fallback order. When a primary provider fails:

  • only fallback for errors that are actually fallbackable;
  • keep the final source label accurate;
  • avoid mixing fields from multiple providers unless the type makes that explicit;
  • return partial data only when the consumer can represent it honestly.

Never fabricate market values to make the UI look complete.

Quotas and costs

Respect free-tier limits. Prefer deterministic caching, throttling, and small response windows over repeated calls.

Do not use Gemini to repair or infer missing provider data. If data is unavailable, report that limitation.

Tests

Mock provider responses for CI. Cover:

  • successful normalization;
  • malformed provider responses;
  • timeout or rate-limit behavior;
  • fallback source attribution;
  • empty data and partial failure cases.
Files

What ships with it

1 file 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. 6d ago First seen · 49 lines · 62 tokens per session scan A 1b38514d45c3

Subscribe to this mod's changes

api-clients is a skill published in the GitHub repository dcosodev/market-inspector (0 stars, last pushed 9d ago), licensed MIT. It adds 62 tokens to every session and 327 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories

x402

Set up Browser Use Cloud payments with x402 — pay per request from a crypto wallet (USDC on Base mainnet), no signup or API key. Two setups it works out up front — "just use it" (set up a wallet so you or Claude Code can run cloud browser tasks paid from the wallet — Claude writes and runs throwaway scripts, nothing…

browser-use/browser-use · 175 tokens

tushare

A Python interface for Tushare, a financial data service that provides market and company information for stocks, funds, futures, and digital assets. It returns queried data as pandas tables.

HKUDS/Vibe-Trading · 79 tokens

stripe-best-practices

Guides Stripe integration decisions across API selection (Checkout Sessions vs PaymentIntents), Connect platform setup (Accounts v2, controller properties), billing/subscriptions, tax and registrations (Stripe Tax, automatictax, product tax codes), Treasury financial accounts, integration options (Checkout, Payment…

stripe/ai · 134 tokens

pinme-uniwebpay

Use when generating, modifying, or reviewing PinMe Worker (Cloudflare Worker TypeScript) code that accepts payments through UniwebPay — payment links, products/prices, checkout sessions, payment status reads, refunds, subscriptions, or handling UniwebPay webhooks with @uniwebpay/sdk in a PinMe project.

glitternetwork/pinme · 71 tokens

erp-xpp

Finance and Operations X++ development lifecycle — scaffold models, author classes, custom services/APIs, and data entities, install matching SDKs, compile deployable packages, deploy packages, synchronize databases, and verify deployed artifacts. Use when the user wants to create, build, compile, package, deploy…

microsoft/Dataverse-skills · 84 tokens

kalshi-api

Kalshi exchange mechanics — RSA-PSS auth, order schema, YES/NO orderbook convention, WebSocket, and endpoint surface. Market-type-agnostic shared layer for all Kalshi skills.

agiprolabs/claude-trading-skills · 44 tokens