agentmods.dev

claude-optimization

claude-optimization is a cursor rule for Cursor from jaycewalzer1/SilverKey-Inc.. It costs 0 tokens per session (533 once invoked), scanned B, original, MIT.

Usage guidance for Claude Code, a coding assistant that works with project files and connected tools. It covers keeping working context focused, excluding files, limiting tool connections, and reducing session noise.

In plain words
What is it for?
Use it when configuring Claude Code sessions, deciding which files or tools to include, and reducing unnecessary context.
Why use it?
It helps prevent irrelevant files and tool output from making coding sessions harder to follow. It also gives guidance for keeping the assistant focused on the current task.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

not rated 2repo 3d ago B scan 0 tokens original MIT

Good fit Use it when configuring Claude Code sessions, deciding which files or tools to include, and reducing unnecessary context.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/jaycewalzer1/silverkey-inc./claude-optimization
View source ↗ jaycewalzer1/SilverKey-Inc.
Install

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.

Clone the repo
git clone --depth 1 https://github.com/jaycewalzer1/SilverKey-Inc.

Made for: Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for claude-optimization

README.md
[![agentmods](https://agentmods.dev/badge/rules/jaycewalzer1/silverkey-inc./claude-optimization/github.svg)](https://agentmods.dev/rules/jaycewalzer1/silverkey-inc./claude-optimization)
Your own site
<a href="https://agentmods.dev/rules/jaycewalzer1/silverkey-inc./claude-optimization"><img src="https://agentmods.dev/badge/rules/jaycewalzer1/silverkey-inc./claude-optimization/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for claude-optimization

Your own site · 80×15
<a href="https://agentmods.dev/rules/jaycewalzer1/silverkey-inc./claude-optimization"><img src="https://agentmods.dev/badge/rules/jaycewalzer1/silverkey-inc./claude-optimization.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 533 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00533
Opus 5.5 $0.00000 $0.00213
Sonnet 5.5 $0.00000 $0.00107
Haiku 4.5 $0.00000 $0.00053

Measured 1mo ago against content hash 8cbb77388bba, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

claude-optimization scanned grade B with 1 finding 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 1mo 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

1. **`permissions.deny`** in [`.claude/settings.json`](../../../.claude/settings.json) — blocks Read, Glob, and Grep on secrets and heavy artifacts.
.cursor/rules/shared/claude-optimization.mdc · 47 lines

What it actually says

Claude Code optimization

Keep this as a short operations guide. Put long tutorials in documentation/reference/.

Session context hygiene

  • Start a fresh Claude Code session for each distinct, unrelated task.
  • Prefer precise @ references to relevant files over broad repo prompts.
  • Use progressive disclosure: scoped .claude/rules/ stubs and skills load on demand; do not paste long guides into prompts.
  • Run /compact when a session grows long; team default autoCompactEnabled: true in .claude/settings.json is a safety net.
  • Run /context to inspect top token consumers; add permissions.deny entries if noisy paths appear.
  • Do not re-run /init over hand-curated CLAUDE.md — it duplicates canonical config.

File exclusion (not .cloudignore)

Claude Code does not use .cloudignore or .claudeignore. SilverKey uses:

  1. permissions.deny in .claude/settings.json — blocks Read, Glob, and Grep on secrets and heavy artifacts.
  2. .gitignore — respected when respectGitignore: true (default in team settings).

MCP usage

  • Daily default: github, linear, slack from mcp.example.json → gitignored mcp.json.
  • Enable high-footprint servers (AWS suites, analytics) only when the task explicitly needs them.
  • Avoid duplicate connector sources (project mcp.json + plugin for the same service).
  • Semantic search MCPs (Code Graph, Cartographer) are optional — scoped rules + GitHub MCP cover most SilverKey work.

Verification feedback loop

  • Use project scripts (make lint, pnpm check, targeted pytest) after edits.
  • Fix newly introduced errors before expanding scope.

References

Changes

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.

  1. 1mo ago First seen · 47 lines · 0 tokens per session scan B 8cbb77388bba

Subscribe to this mod's changes

claude-optimization is a cursor rule published in the GitHub repository jaycewalzer1/SilverKey-Inc. (2 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 533 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents
Related

Other cursor rules, from other repositories

ponytail

Ponytail, lazy senior dev mode. Always pick the simplest solution that works.

DietrichGebert/ponytail · 604 tokens

angular-20

This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.

angular/angular · 0 tokens

dev-standard

Apache Superset development standards and guidelines for Cursor IDE.

apache/superset · 1,147 tokens

prefer-direct-imports-over-module-mocks

Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.

prisma/orm · 0 tokens

config-validation-and-normalization

Config validation and normalization responsibilities (defineConfig normalizes, the orm section schema validates and resolves paths, the loader reports per-section diagnostics).

prisma/orm · 0 tokens

control-plane-descriptors

Control plane descriptor and instance implementation patterns.

prisma/orm · 0 tokens