Skip to main content
skill CX Codex

exa-cost-tuning — Claude Code skill: manage Exa API spend

Skill to control Exa API costs through endpoint selection, result limits, per-key budgets, and response cost tracking. Triggers on "Exa cost tuning", "review Exa cost tuning", or "fix Exa cost tuning".

MIT 1 installs ★ 2,935 updated 2026-10-29

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add jeremylongshore/tons-of-skills-marketplace --skill exa-cost-tuning -a claude-code
Open on GitHub

What exa-cost-tuning does

This skill keeps Exa API spending in check by capping result counts and content types, setting per-key cost ceilings, and tracking each response's price. It works with your repository, environment, Exa team, and owner, establishing names for the budget, workload, endpoint mix, and forecast window. You'll need current Exa pricing docs and credentials only for controlled checks.

The skill reads code and config through Read, Glob, and Grep; writes changes only after approval. It won't create monitors, agents, or API keys just because it was called—it requires the owner's explicit decision. It checks: Search, Contents, Answer, Monitors, and Agent each have different rates; a 402 error may mean account, key, or team credits are exhausted; auto-recharge without a monthly cap can break your budget.

What it helps with

  • Forecast Exa search costs against your monthly budget
  • Set per-endpoint limits on result count and content depth
  • Match query costs in API responses to dashboard billing
  • Configure key-level budgets and cost alerts
  • Validate configuration before enabling live queries

Example prompts for the agent

  • Exa cost tuning for production search, monthly budget 500, owner sidorov
  • review Exa cost tuning in the repo to check keys and limits
  • fix Exa cost tuning—author forgot to cap the auto-recharge

How to install exa-cost-tuning

1Skills CLI (Vercel)

npx skills add jeremylongshore/tons-of-skills-marketplace --skill exa-cost-tuning -a claude-code

2Manually: put the files in place

~/.claude/skills/exa-cost-tuning/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/exa-cost-tuning/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about exa-cost-tuning

How do I install exa-cost-tuning in Claude Code?

Run npx skills add jeremylongshore/tons-of-skills-marketplace --skill exa-cost-tuning -a claude-code, then open ~/.claude/skills/exa-cost-tuning/SKILL.md.

What does exa-cost-tuning do?

It helps you control Exa API spending: cap results and content types, set per-key budgets, track response costs, and monitor credit depletion.

What do I need to use this skill?

Access to your repository, environment, Exa team, and owner approval. For live queries, supply credentials from an approved server-side secret manager only.

Source text

SKILL.md · MIT
---
name: exa-cost-tuning
description: >-
  Control Exa spend through endpoint selection, bounded result and content work, per-key budgets, and response-derived cost evidence. Use when operating or reviewing this Exa boundary. Trigger with "Exa cost tuning", "review Exa cost tuning", or "fix Exa cost tuning".
allowed-tools: Read,Glob,Grep,Write,Edit
argument-hint: "<workload> <monthly-budget> <owner>"
version: 1.12.0
license: MIT
author: Jeremy Longshore <[email protected]>
tags: [saas, exa]
model: inherit
effort: high
compatibility: "Designed for Claude Code; live Exa work requires network access"
---
# Exa Cost and Credit Control

## Overview

Control Exa spend through endpoint selection, bounded result and content work, per-key budgets, and response-derived cost evidence. Treat credentials, queries, retrieved content, generated output, spend, and destructive state as separately governed boundaries.

## Prerequisites

- The target repository, environment, Exa team, product surface, and accountable owner.
- The workload's data classification, latency and freshness promise, cost ceiling, and retention policy.
- Current first-party documentation plus credentials only for a narrowly approved live check.

## Current Contract

Exa uses prepaid pay-as-you-go credits unless an enterprise contract says otherwise. Search, Contents, Answer, Monitors, and Agent have different pricing; additional results, summaries, deep types, provider calls, and metered Agent effort can add cost. Higher credit balance does not raise rate limits.

## Authentication

For normal REST work, inject `EXA_API_KEY` from an approved server-side secret manager and send it only as `Authorization: Bearer` to the configured first-party Exa API host. Team Management service keys, hosted MCP OAuth or enterprise managed authorization, and payment-protocol calls are separate trust models. Never print, commit, place in a URL, or expose a credential to an untrusted client.

## Instructions

1. Name the budget owner, team, workload, endpoint mix, and forecast horizon.
2. Verify current first-party pricing or the signed enterprise schedule.
3. Cap results, content types, subpages, freshness, Agent effort, and retry attempts.
4. Use key-level budgets where enabled and independent application-side circuit breakers.
5. Reconcile response costDollars and dashboard billing against workload identifiers.
6. Alert before credit exhaustion and review auto-recharge with its monthly maximum.

## Tool Discipline

Use Read, Glob, and Grep to inspect repository code, configuration, fixtures, and evidence. Use Write and Edit only for approved implementation or documentation changes. Do not call Exa, run paid research, create or alter a Monitor, Webset, Agent run, Batch, team, member, API key, budget, webhook, or deployment merely because this skill was invoked.

## Approval Boundaries

Require an accountable owner before live queries involving sensitive intent, production credentials, spend or rate-limit changes, forced live crawling, generated summaries, external delivery, deployment, member or key changes, schedule creation, or destructive cancellation, stopping, deletion, or revocation. Read-only repository inspection and synthetic offline validation do not authorize live vendor actions.

## Failure Modes

- Do not hard-code current public prices as permanent business logic.
- A 402 may mean account credits, key budget, or team budget is exhausted.
- Auto-recharge without a monthly maximum can defeat an application budget.

## Output

Return the operation scope, environment, team and product surface, authorization class, contract and policy decisions, deterministic validation results, content-free identifiers, status and cost counts, risks, cleanup or rollback state, and a concise pass or fail receipt. Exclude credentials, raw queries, prompts, presigned URLs, retrieved content, generated output, and customer-derived data unless separately approved.

## Example

- Budget interactive Search separately from Agent research, cap Agent effort, and alert on both response cost and remaining credits.
- Finish with request or resource IDs, assertion counts, cost and terminal state, rollback or deletion status, and the decision owner; never reproduce secrets or retrieved content.

## Validation

Rerun the smallest relevant deterministic test, compare actual behavior with the requested outcome and current first-party contract, verify sensitive fields are absent from evidence, and confirm deadlines, terminal state, downstream retention, and rollback before reporting success.

## References

Review the dated first-party evidence map before relying on any endpoint, parameter, search type, price, limit, beta, compliance, identity, retry, or lifecycle claim.

- [Current first-party evidence map](references/official-docs.md)

© Jeremy Longshore · MIT · jeremylongshore/tons-of-skills-marketplace

Similar skills

All skills for Backend and APIs →

From the same set139

The whole set →
coderabbit-cost-tuning The coderabbit-cost-tuning skill reviews CodeRabbit plans, seats, limits, and usage against current billing evidence. Use it to prepare cost scenarios before anyone approves a change. CX Codex +1 1installs firecrawl-cost-tuning firecrawl-cost-tuning traces where Firecrawl credits go and trims the bill through endpoint choice, format discipline, cache policy and spend limits, checked against quality. CX Codex +1 1installs retellai-cost-tuning retellai-cost-tuning optimizes voice agent and telephony expenses on Retell AI. Helps trim phone call budgets while preserving essential human-handoff triggers. CX Codex +1 1installs groq-cost-tuning groq-cost-tuning — a skill for reducing Groq API costs through model routing, token minimization, and usage tracking. CX Codex +1 1installs setting-up-experiment-tracking setting-up-experiment-tracking configures MLflow or Weights & Biases for machine learning projects, installs packages, and writes code to log parameters, metrics, and artifacts. CX Codex +1 1installs openrouter-streaming-setup openrouter-streaming-setup — a skill for Claude Code, Codex, Cursor and other platforms that implements streaming responses from OpenRouter via Server-Sent Events. CX Codex +1 1installs evernote-core-workflow-a evernote-core-workflow-a — a skill for Claude Code and five other platforms that covers the primary Evernote workflow: note creation, notebook organisation, and tag management. Handles CRUD operations, ENML formatting, and notebook stacks. CX Codex +1 1installs backlog-grooming-assistant backlog-grooming-assistant automates backlog grooming workflows, guides task refinement, and validates project management configurations. CX Codex +1 1installs

Project sponsors

Companies that keep this analytics open