ai-plc-system

ai-plc-system is a cursor rule for Cursor from miyatti777/ai-plc. It costs 522 tokens per session, scanned A, original, MIT.

Root rules for an AI-PLC project, a workflow that organises AI product work into stages from collecting requirements through operation.

In plain words
What is it for?
They are for managing project stages, nested tasks, context sharing, verification, and naming of project artifacts.
Why use it?
They give agents shared rules for breaking down work, structuring files, passing context, and checking results.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc). Also seen: mentions subagents; mentions Claude Code.

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/miyatti777/ai-plc/ai-plc-system
Clone the repo
git clone --depth 1 https://github.com/miyatti777/ai-plc

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 ai-plc-system

README.md
[![agentmods](https://agentmods.dev/badge/rules/miyatti777/ai-plc/ai-plc-system.svg)](https://agentmods.dev/rules/miyatti777/ai-plc/ai-plc-system)
Your own site
<a href="https://agentmods.dev/rules/miyatti777/ai-plc/ai-plc-system"><img src="https://agentmods.dev/badge/rules/miyatti777/ai-plc/ai-plc-system.svg" alt="Measured on agentmods" height="20"></a>
Per session 522 This file is loaded in full into every session.
When invoked 522 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 5.1 $0.00522 $0.00522
Opus 5 $0.00261 $0.00261
Sonnet 5 $0.00104 $0.00104
Haiku 4.5 $0.00052 $0.00052

Measured 6d ago against content hash a8bf9df71d17, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ai-plc-system 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 6d 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/ai-plc-system.mdc · 60 lines

What it actually says

AI-PLC System Rules

This project uses AI-PLC (AI Product Lifecycle) pipeline.

Core Principles

  1. Context Cascade — Parent→Child scope context propagation (immutable / overridable / local)
  2. Fractal Decomposition — Recursive goal decomposition into Sub-Agent Scopes
  3. Adaptive Workflow — Simple / Standard / Complex depth auto-detection
  4. Self-Describing Task — Context-attached task delegation

Skills Location

  • .cursor/skills/ai-plc/01-collection/SKILL.md — Stage 1: Collection
  • .cursor/skills/ai-plc/02-inception/SKILL.md — Stage 2: Inception
  • .cursor/skills/ai-plc/03-construction/SKILL.md — Stage 3: Construction
  • .cursor/skills/ai-plc/04-operation/SKILL.md — Stage 4: Operation

Rules

  • .cursor/rules/ai-plc-system.mdc — This file (root system rules)
  • .cursor/rules/ai-plc-session.mdc — Session management
  • .cursor/rules/ai-plc-adaptive.mdc — Adaptive Workflow depth

Working Directory

Create new work in Flow/[YYYYMM]/[YYYY-MM-DD]/.

Naming Conventions

Prefix System Example
SKL_plc_* Skills SKL_plc_01_collection
RUL_plc_* Rules RUL_plc_system
TPL_* Templates TPL_role_developer

File Names (mandatory)

File Purpose
intent.yaml Execution Context metadata
context.yaml Context Manifest
backlog.yaml Task definitions
Context/ Context Store
Documents/ Artifact Store

Post-Deliver Propagation (mandatory after task completion)

After completing each task, execute the following checklist:

  1. backlog.yaml — Update status to completed + output link
  2. context.yaml — Add artifact entry
  3. native memory — Update user model/preferences (Claude Code native memory; or skip)
  4. Wiki update — Propagate new knowledge to .claude/wiki/
  5. External Sync / log.md / Project Registry — see rules/ai-plc-system.md §8
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. 6d ago First seen · 60 lines · 522 tokens per session scan A a8bf9df71d17

Subscribe to this mod's changes

ai-plc-system is a cursor rule published in the GitHub repository miyatti777/ai-plc (45 stars, last pushed 1mo ago), licensed MIT. It adds 522 tokens to every session, about $0.0026 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 2026-08-30.