50-workflows

A set of rules for starting new projects and bringing existing projects into a standard project setup. It covers selecting an appropriate project profile, adding AI-related project infrastructure, and locating onboarding documentation.

In plain words
What is it for?
Use it when creating a project, adopting an existing codebase, choosing a supported stack profile, bootstrapping project infrastructure, or checking the correct onboarding path.
Why use it?
It reduces setup mistakes by defining which bootstrap process and project profile to use. It also prevents applying stack-specific instructions, such as Laravel or WordPress rules, to the wrong kind of project.

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/conlinjoe/ai-platform/50-workflows
Clone the repo
git clone --depth 1 https://github.com/ConlinJoe/ai-platform

Made for: Cursor.

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,918 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00011 $0.02918
Opus 5 $0.00005 $0.01459
Sonnet 5 $0.00002 $0.00584
Haiku 4.5 $0.00001 $0.00292

Measured 2d ago against content hash 6ca78f9f6f91, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

50-workflows 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.

.cursor/rules/50-workflows.mdc · 299 lines

How it starts

The opening of the file, as written. The whole thing — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.

New Project Workflow

Objective

Start every new project with a consistent AI context, documentation contracts, and ChatGPT export support.

Checklist

  1. Select the appropriate project profile from core/project-profiles/ and create/scaffold the project. Choose the stack intentionally; once scaffolded, treat the installed environment as the starting point. Current profiles: laravel-webapp for Laravel web applications; roots-radicle for Roots Radicle/Sage WordPress projects. Do not apply a profile to a project that is not that stack.
  2. Bootstrap AI Platform infrastructure into the project:
    • Preferred: from the target project root, run /path/to/ai-platform/scripts/bootstrap-project.sh with no argument (uses $PWD when invoked from outside the AI Platform repository).
    • Alternative: from the AI Platform repository, run scripts/bootstrap-project.sh /path/to/project.
    • Fallback: run scripts/bootstrap-project.sh from the AI Platform repository with no argument and supply the target path when prompted. Onboarding for a first-time clone lives in the harness clone: docs/getting-started.md (linked from that repository's README). Do not look for that file in the target project's docs/.
  3. Establish project-specific documentation contracts before substantive feature development. Bootstrap installs templates and shared infrastructure only; it does not populate project truth. Existing projects: after bootstrap, run Project Adoption (core/prompts/project-adoption.md) in a fresh agent session.
  4. Export initial ChatGPT context and upload to your ChatGPT Project.
  5. Begin implementation.

Bootstrap Target Resolution

scripts/bootstrap-project.sh resolves the target project as follows:

  1. Explicit path argument, if supplied
  2. Current working directory ($PWD) when invoked from outside the AI Platform repository
  3. Interactive prompt as the fallback

Read the full file on GitHub · 299 lines

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. 2d ago First seen · 299 lines · 11 tokens per session scan A 6ca78f9f6f91

Subscribe to this mod's changes

50-workflows is a cursor rule published in the GitHub repository ConlinJoe/ai-platform (2 stars, last pushed 4d ago), licensed MIT. It adds 11 tokens to every session and 2,918 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.