cost-report
Skill1 starsChanged 22 days agoMITView on GitHub
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.
5 other projects use a version of this.
Adopted by
Most recently taken up by
- YadavSanjay/ClaudeConfig-Publictheir own version, first seen Nov 1, 2026
- QuixiAI/Hexistheir own version, first seen Oct 8, 2026
- QuixiAI/agi-memorytheir own version, first seen Oct 8, 2026
- jpoindexter/theft-kittheir own version, first seen May 20, 2026
- Manavarya09/cost-guardiantheir own version, first seen Apr 8, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- QuixiAI/agi-memory★ 623same name
- QuixiAI/Hexis★ 623same name
- Manavarya09/cost-guardian★ 35same name
- jpoindexter/theft-kit★ 1same name
- YadavSanjay/ClaudeConfig-Public★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository7 other files it gives its agents.
- build-custom-agentSkill
- build-template-agentSkill
- coverage-gapsSkill
- generate-evalSkill
- health-checkSkill
- instrument-agentSkill
- trace-triageSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Read references/mcp.md first for the tool contract and limits.
- Distinctive: line 43
Keep it tight — a few bullets and one small table, not a wall of numbers.
- Distinctive: line 45
Never write back to the platform — the server is read-only.
“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
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.
<!-- copilot:start -->Turn the platform's cost and usage data into a short, decision-ready report.
Workflow
- Scope. Confirm the date range (
get_cost_breakdowntakesstart_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_summaryfor 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.
<!-- copilot:end -->Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.