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 rules/saski/arnesto/cursor-config-managementgit clone --depth 1 https://github.com/saski/arnestoWrote 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.
[](https://agentmods.dev/rules/saski/arnesto/cursor-config-management)<a href="https://agentmods.dev/rules/saski/arnesto/cursor-config-management"><img src="https://agentmods.dev/badge/rules/saski/arnesto/cursor-config-management.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00674 | $0.00674 |
| Opus 5 | $0.00337 | $0.00337 |
| Sonnet 5 | $0.00135 | $0.00135 |
| Haiku 4.5 | $0.00067 | $0.00067 |
Grade B, and why
cursor-config-management 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 today.
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.
- **Managed Codex Config**: `~/.codex/rules/default.rules`, `~/.codex/AGENTS.md`, and `~/.codex/hooks/rtk-rewrite.sh` are symlinked to repo; `~/.codex/config.toml` and `~/.codex/hooks.json` are copied from `templates/cod How it starts
The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cursor Configuration Management
Canonical Source
- Repository: the current Arnesto checkout
- GitHub:
github.com/saski/arnesto - Global Config:
~/.cursor/commands/(symlink to repo). Cursor rules in.cursor/rules/apply only when this repo is open; the universal rulebook reaches every Cursor workspace via~/AGENTS.md→.agents/rules/base.md. - Managed Cursor Config:
~/.cursor/mcp.jsonand~/.cursor/cli-config.json(symlinked to repo) - Managed Codex Config:
~/.codex/rules/default.rules,~/.codex/AGENTS.md, and~/.codex/hooks/rtk-rewrite.share symlinked to repo;~/.codex/config.tomland~/.codex/hooks.jsonare copied fromtemplates/codex/ - Managed Gemini Config:
~/.gemini/antigravity/mcp_config.jsonand~/.gemini/GEMINI.md(symlinked to repo) - Canonical .agents Link:
~/.agentsshould be a symlink to repo.agents/(no local duplicate) - Shared Skills:
.agents/skills/— canonical skill root; exposed to Cursor (and Codex, Antigravity, etc.) via symlinks (e.g.~/.cursor/skills→ repo.agents/skills/). Includes native skills plus imported upstream skills tracked in this repo. Agents should consider all skills in this directory when the user's request matches a skill description; read the skill'sSKILL.mdand follow its instructions. For skill usage and discovery, follow the Skills section in.agents/rules/base.mdand the index in.agents/docs/.
This repository is the single source of truth for all Cursor IDE configuration. Global config is symlinked to the repo.
Symlink Workflow
The repository uses symlinks for configuration. Use setup-symlinks.sh for:
- Initial setup:
./setup-symlinks.sh setup - Validation:
./setup-symlinks.sh validate - Commit changes:
./setup-symlinks.sh commit
Setup on New Machine
cd /path/to/arnesto
./setup-symlinks.sh setup
Verify Symlinks
./setup-symlinks.sh validate
Reminder
Edits in Cursor (to rules, commands, skills) modify the repo files directly. Commit with ./setup-symlinks.sh commit or standard git workflow.
Runtime state files generated by tools (sessions/history/cache/UI state) are intentionally local and not canonicalized. For mutable config files such as ~/.codex/config.toml and ~/.claude/settings.json, this repo stores templates and seeds local files during setup rather than symlinking those mutable files back into the repo.
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.
- today First seen · 47 lines · 674 tokens per session scan B cb5057567f67
cursor-config-management is a cursor rule published in the GitHub repository saski/arnesto (5 stars, last pushed 8d ago), licensed Unlicense. It adds 674 tokens to every session, about $0.0034 per session on Opus 5. 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 2026-09-03.
Other cursor rules, from other repositories
coding-guardrails
Unified coding guardrails (Top Thinkers System) — synced from AGENTS.md.
cursorrules
These guidelines enforce discipline, conceptual clarity, and simplicity.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
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.