agentmods.dev

global

global is a cursor rule for Cursor from systemowiec/ai-agents-workspace-starter. It costs 554 tokens per session, scanned A, original, MIT.

A project-wide rule set that defines how code, documentation, architecture, commands, and Git work are handled. It makes AGENTS.md the main source of truth and requires work to run through Docker and the project's documented workflow.

In plain words
What is it for?
Use it to guide everyday development, including command execution, code structure, formatting, commit names, branches, planning, and verification.
Why use it?
It prevents contributors from using inconsistent commands or bypassing required reviews, documentation, and architecture rules. It also gives the coding agent one place to check project expectations.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions AGENTS.md.

not rated 2repo 7mo ago A scan 554 tokens original MIT

Good fit Use it to guide everyday development, including command execution, code structure, formatting, commit names, branches, planning, and verification.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/systemowiec/ai-agents-workspace-starter/global
View source ↗ systemowiec/ai-agents-workspace-starter
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/systemowiec/ai-agents-workspace-starter

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 global

README.md
[![agentmods](https://agentmods.dev/badge/rules/systemowiec/ai-agents-workspace-starter/global/github.svg)](https://agentmods.dev/rules/systemowiec/ai-agents-workspace-starter/global)
Your own site
<a href="https://agentmods.dev/rules/systemowiec/ai-agents-workspace-starter/global"><img src="https://agentmods.dev/badge/rules/systemowiec/ai-agents-workspace-starter/global/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 global

Your own site · 80×15
<a href="https://agentmods.dev/rules/systemowiec/ai-agents-workspace-starter/global"><img src="https://agentmods.dev/badge/rules/systemowiec/ai-agents-workspace-starter/global.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 554 This file is loaded in full into every session.
When invoked 554 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.00554 $0.00554
Opus 5.5 $0.00222 $0.00222
Sonnet 5.5 $0.00111 $0.00111
Haiku 4.5 $0.00055 $0.00055

Measured 2mo ago against content hash a6968b6d02d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

global 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 2mo 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.

.cursor/rules/global.mdc · 57 lines

What it actually says

Global Rules

Read AGENTS.md - the single source of truth for ALL project rules.

Docker First - ABSOLUTELY

  • NEVER run commands locally. Only make / docker compose.
  • Forbidden: python3, pip, npm, npx, pytest, ruff, mypy, alembic
  • Allowed: make test, make lint, make up, make shell, make build

4 Cardinal Rules

  1. Quality-First - best solution always. Proactive improvements.
  2. Documentation First - docs BEFORE code. Documentation = source of truth.
  3. Docker First - NEVER locally. Only make / docker compose.
  4. Plan -> Review -> Implementation - WAIT for acceptance.

Architecture

  • Hexagonal Architecture (Ports & Adapters)
  • Order: domain -> application -> adapters -> interface
  • Full details in AGENTS.md section 5

Formatting

  • NEVER use typographic dashes (em-dash, en-dash). Only - (ASCII 45)
  • Conventional commits: feat:, fix:, refactor:, test:, docs:, infra:, ci:
  • Branch: feat/{PREFIX}-NNN-description, fix/{PREFIX}-NNN-description (per .agents/rules/git-workflow.md)

Workflow

EVERY task MUST go through .agents/workflows/spec-development.md

  1. Problem analysis
  2. PLAN (bullet points)
  3. Wait for acceptance
  4. Documentation (BEFORE code!)
  5. Implementation
  6. Verification (.agents/workflows/post-impl-verify.md)
  7. Summary + diff of changes

Agent Resources

  • AGENTS.md - full rules (READ FIRST)
  • .agents/roles/ - role definitions (analyst, architect, backend-engineer, frontend-engineer, platform-engineer, e2e-engineer, ai-specialist, quality-gate)
  • .agents/skills/ - code patterns and procedures
  • .agents/workflows/ - processes (dt-development, post-impl-verify, create-dt, complete-dt)
  • .agents/rules/ - global rules and git workflow
  • .agents/learnings/ - pitfalls and unusual behaviors
  • docs/templates/ - spec templates, reports, modules
  • docs/specs/ - spec directories with scope, impl and review reports
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. 2mo ago First seen · 57 lines · 554 tokens per session scan A a6968b6d02d9

Subscribe to this mod's changes

global is a cursor rule published in the GitHub repository systemowiec/ai-agents-workspace-starter (2 stars, last pushed 7mo ago), licensed MIT. It adds 554 tokens to every session, about $0.0022 per session on Opus 5.5. 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.

Git and workflowProject management
Related

Other cursor rules, from other repositories

changesets

Changeset format and bump rules enforced by CI.

adobe/spectrum-design-data · 0 tokens

project-context

Current repository context, commands, and documentation authority.

vypdev/copilot · 279 tokens

iris

GitHub operations specialist — branches, pull requests, issues, releases, tags. Called by zeus after review. Never pushes or merges without explicit human approval. Integrates with VS Code GitHub Pull Requests extension.

ils15/pantheon-legacy · 43 tokens

github-repo-triage

Triage and maintain GitHub repos — issues, PRs, cherry-picks, releases, publishing.

cdbattags/ai · 459 tokens

git_rules

When asked to interact with git, github or project management tooling (jira, linear, asana etc).

nirbenz/cursor-mcp-examples · 21 tokens

ponytail

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

DietrichGebert/ponytail · 604 tokens