Purpose: Query token allowance and usage for the team tied to the current API key — pre-flight checks or admin reports only; produces no content.
When to use:
Pre-flight before large jobs: “Can we still run research-agent?” → action=check
Admin reporting: “How many tokens did we use this month?” → action=count
Agent orchestration: auto-guard before expensive workflows
When NOT to use:
Any content production (research, reading, memory) — use research-agent, deep-reading, or remember-and-recall
Substitute for Host LLM chat or reasoning — smart_budget_guard is not a completion API
Record per-task consumption — runtime uses action=record after tool calls (out of scope for this workflow)
Returns: JSON string. check: data.allowed (boolean), data.remaining, data.limit, data.used. count: data.used, data.period, data.breakdown (by tool or time bucket, if present).
Composes with: loader or Host calls check before research-agent / deep-reading; show count results directly to admins.
1---2name: usage-report3description: usage-report4---5## usage-report67Purpose: Query token allowance and usage for the team tied to the current API key — pre-flight checks or admin reports only; produces no content.89When to use:10- Pre-flight before large jobs: “Can we still run research-agent?” → action=check11- Admin reporting: “How many tokens did we use this month?” → action=count12- Agent orchestration: auto-guard before expensive workflows1314When NOT to use:15- Any content production (research, reading, memory) — use **research-agent**, **deep-reading**, or **remember-and-recall**16- Substitute for Host LLM chat or reasoning — smart_budget_guard is not a completion API17- Record per-task consumption — runtime uses action=record after tool calls (out of scope for this workflow)1819Returns: JSON string. `check`: `data.allowed` (boolean), `data.remaining`, `data.limit`, `data.used`. `count`: `data.used`, `data.period`, `data.breakdown` (by tool or time bucket, if present).2021Composes with: loader or Host calls check before **research-agent** / **deep-reading**; show count results directly to admins.
Run npx skillmds@latest add smartgate-network/usage-report in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
usage-report It is listed under Docs & Writing on SkillMD.
This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
smartgate-network (@smartgate-network) published this skill. Their other Agent Skills are listed on their SkillMD profile.
smartgate-network