main

A set of project rules, commands, and agent roles for Cursor, an AI coding editor. It tells the editor where project guidance lives and what checks to run before changes are finished.

In plain words
What is it for?
Use it to plan work, build features, review code or design, audit dependencies, choose models, learn the project, and manage worktrees.
Why use it?
It keeps coding work consistent with the repository’s rules and makes reviews and safety checks easier to follow.

Cursor rule for Cursor

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.

agentmods
npx agentmods add rules/bita71/agent-workflow-kit/main
Clone the repo
git clone --depth 1 https://github.com/Bita71/Agent-Workflow-Kit

Made for: Cursor.

Per session 385 This file is loaded in full into every session.
When invoked 385 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00385 $0.00385
Opus 5 $0.00192 $0.00192
Sonnet 5 $0.00077 $0.00077
Haiku 4.5 $0.00038 $0.00038

Measured yesterday against content hash 7b30ed15cd3c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

main 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.

.cursor/rules/main.mdc · 39 lines

What it actually says

Cursor Adapter

docs/ai is the source of truth for rules, skills, commands, agent roles, and artifacts. Before working, read:

  • .agent-workflow-kit/config.conf — project settings and active profiles.
  • docs/ai/README.md — map of the AI surface.
  • docs/ai/rules/project.md — tool-agnostic invariants (scope, clarify, safety, verification).
  • docs/ai/rules/coding-rules.md — this stack's conventions.
  • docs/ai/rules/commit-message.md — Conventional Commits.

<check> means CHECK_COMMAND from the config. Run it after substantive changes unless it is none. Do not commit or push without an explicit request.

Commands

Cursor slash commands live in .cursor/commands/* as thin adapters that point into docs/ai/commands/*. Available: symphony, codex-plan, build, review-full, review-design, choose-model, ai-audit, deps-audit, learn, apply-worktree.

Roles

  • Planning and correctness/security review run through Codex (docs/ai/agents/cli.md, docs/ai/agents/codex-plan.md, docs/ai/agents/review-correctness.md, docs/ai/agents/review-security.md).
  • Implementation and design review use the tracked Cursor agents build and review-design (docs/ai/agents/build.md, docs/ai/agents/review-design.md).

Resolve model roles and effort through config and docs/ai/commands/choose-model.md. Do not restate rules in replies; follow the referenced files.

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. yesterday First seen · 39 lines · 385 tokens per session scan A 7b30ed15cd3c

Subscribe to this mod's changes

main is a cursor rule published in the GitHub repository Bita71/Agent-Workflow-Kit (1 stars, last pushed 1mo ago), licensed MIT. It adds 385 tokens to every session, about $0.0019 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.