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/emaraschio/cursor-commands/optimize-performancegit clone --depth 1 https://github.com/emaraschio/cursor-commandsWhat 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 | $0.00011 | $0.00398 |
| Opus 5 | $0.00005 | $0.00199 |
| Sonnet 5 | $0.00002 | $0.00080 |
| Haiku 4.5 | $0.00001 | $0.00040 |
Grade A, and why
optimize-performance 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 2d ago.
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.
What it actually says
Overview
Profile and optimize performance bottlenecks. Full workflow: .cursor/skill-contracts/optimize-performance/SKILL.md (user install: ~/.cursor/skill-contracts/optimize-performance/SKILL.md).
Defaults
None. See skill for workflow defaults.
Steps
- Read
.cursor/skill-contracts/optimize-performance/SKILL.mdfor the full agent contract; if that file is missing, read~/.cursor/skill-contracts/optimize-performance/SKILL.md. - Execute the workflow in order; do not skip safety steps.
- Report outcomes per skill (summary, tables, or checklist as specified).
Anti-patterns
- Measure before optimizing. Trigger: a suspected performance problem. Wrong: rewriting code based on a guess about what is slow. Correct: profile to find the real bottleneck, then optimize it. Reason: unmeasured optimizations often target the wrong code and add complexity for no gain.
- Do not trade readability for micro-gains. Trigger: a change that shaves a negligible amount of time. Wrong: obscuring the code for an unmeasurable speedup. Correct: keep the readable version unless the gain is significant and measured. Reason: unreadable code costs more in maintenance than a micro-optimization saves.
Examples
/optimize-performance
Maintainers
Behavioral eval: .cursor/skill-contracts/optimize-performance/eval/cases.md. Ship gate sections: A, S before changing SKILL.md or this command.
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.
- 2d ago First seen · 38 lines · 11 tokens per session scan A 36707ee9068f
optimize-performance is a command published in the GitHub repository emaraschio/cursor-commands (9 stars, last pushed 26d ago), licensed MIT. It adds 11 tokens to every session and 398 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
grok_execute
Explicitly turn the task-local Grok executor mode on or off.
thirdparty-web-interface-guidelines
Review these files for compliance: $ARGUMENTS.
plan
Research, clarify requirements, and produce an approved implementation plan before writing code (Cursor Plan Mode).
green-repo
Drive the whole repository to a verified-green baseline — typecheck, lint, tests, build — with authorized fixing of pre-existing debt.
ship-and-observe
Take merged, green code to a verified, monitored production release — deploy, confirm the revision is live, smoke-test, observe, and roll back if needed.
gate-logic
Audit CI/CD gate logic — silent bypass, ratchet gaming, conflicting conditions — report only.