instantly-cost-tuning — Claude Code skill: usage and install
The instantly-cost-tuning skill reviews Instantly usage and compares plan and account-capacity options. Use it when assessing workspace consumption before a capacity decision.
MIT 1 installs ★ 2,935 updated 2026-10-29
npx skills add jeremylongshore/tons-of-skills-marketplace --skill instantly-cost-tuning -a claude-codeWhat instantly-cost-tuning does
The skill gathers plan and subscription details, active and idle account counts, campaign outcomes, and verification and enrichment usage. It compares keeping, consolidating, or expanding capacity, then records assumptions, evidence, approval status, and a next action. Pricing and limits come from current sources rather than fixed values in the analysis.
Live API checks require network access, an approved Instantly workspace, and an API v2 key with the relevant permissions. Reading billing data requires the workspace_billing scope. The skill uses file-reading tools and web requests; it uses Write or Edit only when implementation was requested and the exact files are known. Diagnosis stays read-only by default, so plan, account, and paid-capacity changes need approval from the accountable owner.
What it helps with
- measure Instantly plan and subscription usage
- compare active accounts with idle ones
- weigh options to keep, consolidate, or expand account capacity
- prepare a cost decision with supporting evidence and assumptions
Example prompts for the agent
- Audit Instantly usage for
last-30-daysand estimate cost per qualified reply. - Compare keeping, consolidating, and expanding accounts in my Instantly workspace.
- Review verification and enrichment usage, gather evidence, and list the API scopes required.
How to install instantly-cost-tuning
1Skills CLI (Vercel)
npx skills add jeremylongshore/tons-of-skills-marketplace --skill instantly-cost-tuning -a claude-code2Manually: put the files in place
~/.claude/skills/instantly-cost-tuning/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/instantly-cost-tuning/
1Skills CLI (Vercel)
npx skills add jeremylongshore/tons-of-skills-marketplace --skill instantly-cost-tuning -a codex2Manually: put the files in place
.agents/skills/instantly-cost-tuning/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add jeremylongshore/tons-of-skills-marketplace --skill instantly-cost-tuning -a cursor2Manually: put the files in place
.cursor/skills/instantly-cost-tuning/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install jeremylongshore/tons-of-skills-marketplace skills/.curated/instantly-cost-tuning2Manually: put the files in place
.github/skills/instantly-cost-tuning/SKILL.md1Skills CLI (Vercel)
npx skills add jeremylongshore/tons-of-skills-marketplace --skill instantly-cost-tuning -a gemini-cli2Platform CLI
gemini skills install https://github.com/jeremylongshore/tons-of-skills-marketplace --path skills/.curated/instantly-cost-tuningManually: put the files in place
.devin/skills/instantly-cost-tuning/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add jeremylongshore/tons-of-skills-marketplace --skill instantly-cost-tuning -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about instantly-cost-tuning
How do I install instantly-cost-tuning in Claude Code?
Run npx skills add jeremylongshore/tons-of-skills-marketplace --skill instantly-cost-tuning -a claude-code. The skill file is installed at ~/.claude/skills/instantly-cost-tuning/SKILL.md.
What does instantly-cost-tuning do?
It reviews Instantly consumption and compares plan and account-capacity options. The handoff records evidence, assumptions, and approval status.
What do I need for a live API check?
You need network access, an approved Instantly workspace, and an API v2 key with the required permissions. Billing reads require the workspace_billing scope.
Source text
SKILL.md · MIT
--- name: instantly-cost-tuning description: >- Measure Instantly plan, account, verification, and enrichment usage without embedding stale prices. Use when reviewing workspace consumption or preparing a plan-capacity decision. Trigger with "audit Instantly usage", "estimate Instantly capacity", or "review Instantly plan consumption". argument-hint: "[billing-period] [workspace]" allowed-tools: Read, Glob, Grep, WebFetch, Write, Edit version: 1.13.0 author: Jeremy Longshore <[email protected]> license: MIT tags: - saas - instantly - cost-tuning model: inherit effort: high compatibility: Designed for Claude Code; live verification requires network access and an approved Instantly workspace and API v2 key --- # Instantly Cost and Capacity Governance ## Overview Produce an evidence-backed capacity and spend recommendation using live workspace billing and pricing sources. Record assumptions, evidence, approval state, and rollback ownership so another operator can reproduce the result. ## Prerequisites - The target repository, Instantly workspace, environment, and accountable owner - Current security, privacy, compliance, capacity, and change-control requirements - An approved API v2 key only when a bounded live verification is necessary ## Tool Discipline Use `Read`, `Glob`, and `Grep` to inspect code, configuration, and evidence. Use `WebFetch` only for current first-party Instantly documentation and package metadata. Use `Write` or `Edit` only when implementation was requested and exact target files are known; never write credentials, lead data, email content, or unrestricted environment output. ## Current Contract - Pricing and entitlements are dynamic; never hard-code a monthly price or account allowance. - Workspace billing endpoints require workspace_billing read scope. - Some endpoints publish independent limits or credit costs, so general API throughput is not a spend model. ## Authentication Use an API v2 key as `Authorization: Bearer <key>` against `https://api.instantly.ai/api/v2`. Grant only the endpoint-specific scopes needed, inject the key from an approved server-side secret manager, and never print, persist, commit, or place it in a URL. Treat key creation, rotation, revocation, member changes, workspace delegation, and production access as owner-approved actions. ## Instructions 1. Define the billing period, business outcome, sending-account inventory, and cost owner. 2. Read current plan and subscription details with read-only billing scope when available. 3. Measure active versus idle accounts, campaign outcomes, verification, and enrichment consumption. 4. Fetch current first-party pricing and contract terms before making a recommendation. 5. Model keep, consolidate, and expand options with assumptions and sensitivity ranges. 6. Require owner approval for plan, account, domain, or paid-enrichment changes. ## Approval Boundaries Do not create, rotate, reveal, or revoke keys; invite or remove members; delegate across workspaces; connect sending accounts; create or activate campaigns; import or delete leads; change suppression or retention; register, patch, resume, or delete webhooks; alter plans or paid capacity; transmit diagnostics; or perform another production mutation without explicit approval from the accountable owner. Keep diagnosis read-only unless implementation was requested. ## Output Return the workspace-safe scope, files and contracts inspected, exact API v2 routes and required scopes, evidence collected, validation result, sensitive fields redacted, remaining risk, accountable owner, approval state, and rollback or next action. ## Error Handling | Condition | Response | |---|---| | `401` | Stop and verify that the bearer key exists, is current, and was not revoked. | | `403` | Stop and compare the operation with its exact required scope; do not broaden to `all:all` by default. | | `429` | Coordinate the workspace-wide budget, honor endpoint overrides, and bound retries. | | Schema or tenant mismatch | Fail closed, preserve redacted evidence, and do not retry a mutation. | ## Examples Use a compact handoff that makes scope, mutation authority, and evidence reviewable. Input: ```text period=last-30-days; objective=cost-per-qualified-reply ``` Expected handoff: ```text baseline=measured; options=3; prices=live-sourced; decision=awaiting-owner ``` ## Resources - [Skill-specific official documentation](references/official-docs.md) - [Instantly API v2 documentation](https://developer.instantly.ai/) - [Instantly API v2 OpenAPI document](https://api.instantly.ai/openapi/api_v2.json)
© Jeremy Longshore · MIT · jeremylongshore/tons-of-skills-marketplace