How do I install the Cost Report skill?

Run npx skillmds@latest add telerik/cost-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.

Is Cost Report safe to use?

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.

Which AI agents work with Cost Report?

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.

Is Cost Report free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Cost Report?

telerik (@telerik) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Cost Report by telerik — Agent Skill

Name: Cost Report
Author: telerik

Cost Report

Report and explain LLM spend and usage on the Progress Observability Platform. Use when the user asks "what's driving my LLM costs", "how much am I spending", "cost by model/app", "am I close to my quota", "why did spend spike", or wants a cost/usage summary or a cheaper-model recommendation.

telerik 6bd9f0e 2 files · 7.1 KB Updated Sep 17, 2026

File contents

Cost & usage report

Read references/mcp.md first for the tool contract and limits. This skill uses only metadata tools — no trace content, so no injection surface. If that file isn't present (this skill was lifted out on its own), ask the user for the plugin's references/mcp.md, or fall back to the hard rules: every tool is read-only, and get_cost_breakdown / get_usage_summary are the only tools this skill needs.

Turn the platform's cost and usage data into a short, decision-ready report.

Workflow

Scope. Confirm the date range (get_cost_breakdown takes start_date / end_date) and what the user cares about — total spend, a suspected spike, model mix, or quota headroom. Default to the last 7 days if unspecified.
Pull cost. get_cost_breakdown. Run it more than once when useful: group_by: "model" for model mix, "application" for which app spends, "day" for the trend. Use "all" for a first pass.
Pull usage/quota. get_usage_summary for current billing-period usage and remaining quota.
Report.
- Headline — total spend for the range and where the billing period stands vs. quota.
- Top drivers — the models/apps carrying most cost, with shares.
- Trend — day-over-day movement; call out any spike and which model/app it came from.
- Quota — projected burn vs. remaining (extrapolate linearly from period-to-date usage — state that assumption), and whether the current rate lands over quota before the period ends.
- Recommendation (only if the data supports it) — e.g. a high-volume, low- stakes call path that could move to a cheaper model; frame it as a hypothesis to validate, not a certainty.

Keep it tight — a few bullets and one small table, not a wall of numbers.

Never write back to the platform — the server is read-only.

---name: cost-reportdescription: Report and explain LLM spend and usage on the Progress Observability Platform. Use when the user asks "what's driving my LLM costs", "how much am I spending", "cost by model/app", "am I close to my quota", "why did spend spike", or wants a cost/usage summary or a cheaper-model recommendation.---# Cost & usage reportRead `references/mcp.md` first for the tool contract and limits. This skilluses only metadata tools — no trace content, so no injection surface. If that fileisn't present (this skill was lifted out on its own), ask the user for the plugin's`references/mcp.md`, or fall back to the hard rules: every tool is read-only, and`get_cost_breakdown` / `get_usage_summary` are the only tools this skill needs.Turn the platform's cost and usage data into a short, decision-ready report.## Workflow1. **Scope.** Confirm the date range (`get_cost_breakdown` takes `start_date` / `end_date`) and what the user cares about — total spend, a suspected spike, model mix, or quota headroom. Default to the last 7 days if unspecified.2. **Pull cost.** `get_cost_breakdown`. Run it more than once when useful: `group_by: "model"` for model mix, `"application"` for which app spends, `"day"` for the trend. Use `"all"` for a first pass.3. **Pull usage/quota.** `get_usage_summary` for current billing-period usage and remaining quota.4. **Report.** - **Headline** — total spend for the range and where the billing period stands vs. quota. - **Top drivers** — the models/apps carrying most cost, with shares. - **Trend** — day-over-day movement; call out any spike and which model/app it came from. - **Quota** — projected burn vs. remaining (extrapolate linearly from period-to-date usage — state that assumption), and whether the current rate lands over quota before the period ends. - **Recommendation** (only if the data supports it) — e.g. a high-volume, low- stakes call path that could move to a cheaper model; frame it as a hypothesis to validate, not a certainty.Keep it tight — a few bullets and one small table, not a wall of numbers.Never write back to the platform — the server is read-only.

Frequently asked questions