Skip to content

discolike/discolike-skills / skills/explain-usage-and-billing

explain-usage-and-billing

Verified

Use when the user asks "where did my credits go", "why is my balance empty", "when do credits refill", "did my top-up land", or "how much will this cost". Follow the `discolike` skill's access and spend rules.

FileKindSize
SKILL.mdskill md3.5 KB
---
name: explain-usage-and-billing
description: Use when the user asks "where did my credits go", "why is my balance empty", "when do credits refill", "did my top-up land", or "how much will this cost". Follow the `discolike` skill's access and spend rules.
allowed-tools: Read, Grep
---

# Explain usage and billing

Follow the `discolike` skill's How to work rules first.

1. **Check the account.** Reuse the session's MCP `account-status` response when current. The tool returns `plan`, `has_quota`, `cycle_ends_at` (which can be null), `features`, `limits` (`company_exclusion_list_size` and `contact_exclusion_list_size`), and `usage`. Read `quota_status` when present to distinguish exhausted quota from a pending cycle transition. Both account and usage information remain available when data tools are blocked.
2. **Read usage.** MCP `usage-statistics` accepts an optional `fields` list. Read `account_status`, `month_to_date_requests`, `month_to_date_records`, and the trailing 30-day totals `recent_companies_billed`, `recent_contacts_billed`, `recent_emails_billed`, and `recent_records_billed`. Use `usage_summary` for month-by-month activity with `access_id`, `description`, `requests`, and `total_records` per entry. The tool substitutes the description for non-email access IDs. For balance or top-up questions, REST `GET /v1/usage`, CLI `discolike account usage --format json`, and SDK `client.account.usage()` access the usage endpoint. Its `month_to_date_spend`, `total_available_spend`, `carryover_credits`, `top_up_credits`, and `billing_events` are omitted from MCP. Use the account's payment history to confirm a specific payment.
3. **Explain what used credits.** Requests are counted but have no standalone query fee. Standard data charges use billable records at the plan's rate per 1,000 records. Some operations define the unit differently: bulk company matching counts each processed company-name query that did not fail in search as one record. Matching-company counts are free. For net-new company discovery and firmographic enrichment, the reuse window is 24 hours on Pay as you go and 30 days on subscriptions. For validated contact delivery, use the core skill's pricing: 5 records per delivered contact, with a $10 per 1,000 contacts floor, plus 1 record per net-new company delivering at least one when no company list was supplied. LinkedIn contacts delivered without an email (`include_linkedin_only`) cost 1 record each. Repeated contact deliveries are billable. For estimates, use the applicable billable units and the verified account rate.
4. **Explain when credits change.** Use `cycle_ends_at` for the current cycle end. On eligible renewals, unused plan credits and prior carryover can roll forward, capped at one cycle's plan allowance, adjusted for upgrade proration and any lower new allowance. Cancellation clears carryover. Top-ups cover spend after plan and carryover credits, and unused top-ups survive cycle changes. One-click top-up credits are applied when the payment webhook processes. A mid-cycle upgrade prorates the price difference for the rest of the cycle, and the quota adjustment clears at renewal. Pay as you go (plan `free`) has no recurring allowance and uses available credit at its standard rate of $5 per 1,000 records.
5. **Handle gaps and disputes.** Explain what the account and usage numbers show. If the rate, balance, refill, or a specific transaction cannot be verified, say which figure is unavailable. Never promise refunds or credits. Direct billing disputes to support@discolike.com.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall