Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/ofershap/cursor-usage/usage-reportgit clone --depth 1 https://github.com/ofershap/cursor-usageWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00017 | $0.00288 |
| Opus 5 | $0.00009 | $0.00144 |
| Sonnet 5 | $0.00003 | $0.00058 |
| Haiku 4.5 | $0.00002 | $0.00029 |
Grade A, and why
usage-report scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- usage-report — 100% identical, 0 lines differ
What it actually says
Usage Report
Generate a team usage report by following these steps:
- Call
get_team_overviewto get the high-level summary (members, spend, DAU, top models). - Call
get_spendingwithallPages: trueto get the full spending breakdown. - Call
get_model_usagefor the last 7 days to show recent model adoption trends. - Call
get_agent_editsfor the last 7 days to show AI effectiveness metrics.
Present the report in this structure:
Team Summary
- Total members, active members, DAU trend
- Total spend this cycle, average per member
- Billing cycle dates
Spending Breakdown
- Top 10 spenders with amounts
- Spend distribution (median, p75, p90, max)
- Anyone exceeding 3x the median (flag as potential concern)
Model Adoption
- Top 5 models by message volume
- Premium vs standard model split
- Any model concentration risks
AI Effectiveness
- Agent edit acceptance rate
- Tab completion acceptance rate
- Lines of code accepted vs suggested
Recommendations
- Cost optimization opportunities (reference the cursor-cost-optimization skill)
- Users who might benefit from model guidance
- Any anomalies worth investigating
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 46 lines · 17 tokens per session scan A 9cdc5f4ef7e5
usage-report is a command published in the GitHub repository ofershap/cursor-usage (8 stars, last pushed 6mo ago), licensed MIT. It adds 17 tokens to every session and 288 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
self-audit
Run npm run scan from the repository root. This repo must report L4 · Self-correcting.
review
Review the current diff for violations of the conventions in AGENTS.md and .cursor/rules/. Report findings ordered by severity; do not fix anything unless asked.
/spectra-propose
Create a complete change proposal with all artifacts in a single workflow.
/spectra-discuss
Have a focused discussion about a topic and reach a conclusion.
/spectra-ingest
Update an existing Spectra change from a plan file or conversation context.
add-memory
Add a new memory to the current project.