Repository rules that tell a coding agent which project documents to read before making changes. They identify canonical specifications, feature records, implementation packets, and special commands.

Use them when starting non-trivial changes, checking related features, following implementation packets, or handling the project's structured commands.

They help the agent use the project's intended sources and avoid relying on outdated runtime notes or incomplete context.

cursorrules — Cursor rule by RobLovesTech

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/roblovestech/agenticflywheel/cursorrules

Clone the repo

git clone --depth 1 https://github.com/RobLovesTech/AgenticFlyWheel

Made for: Cursor.

Per session 962 This file is loaded in full into every session.

When invoked 962 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.

Model	Per session	Once invoked
Fable 5	$0.00962	$0.00962
Opus 5	$0.00481	$0.00481
Sonnet 5	$0.00192	$0.00192
Haiku 4.5	$0.00096	$0.00096

Measured yesterday against content hash fb9d1819c4df, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursorrules 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.

templates/config/.cursor/rules/.cursorrules · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AgenticFlywheel Framework Integration

Canonical Sources

Before making changes, read in this order:

AGENTS.md
docs/ai/INDEX.md
docs/AIP_FRAMEWORK.md
AgenticFlywheel/spec/EXECUTION_LAYER.md
docs/features/REGISTRY.yaml
The target packet under docs/Agent Implementation Packets/<feature-slug>/

Packet docs are canonical. Runtime artifacts under .agentic-flywheel/state/ are advisory only.

Context Gathering (Automatic)

Before non-trivial changes:

Check docs/features/REGISTRY.yaml for related features and dependencies
Search docs/Agent Implementation Packets/*/ for similar patterns
Read REVIEWS.md if the packet exists
Review docs/ai/INDEX.md and linked standards

Natural Command Routing

Treat these phrases as structured intents:

new AIP, create AIP for <feature>, start AIP for this change → active collaboration with AgenticFlywheel/prompts/AIP_COLLAB.md; use AgenticFlywheel/prompts/AIP_NEW.md only after collaboration readiness is satisfied or the user explicitly requests direct/template-only scaffolding
update AFW, import AFW update, upgrade AgenticFlywheel → AgenticFlywheel/prompts/AFW_IMPORT_UPDATE.md
office hours → AgenticFlywheel/prompts/OFFICE_HOURS.md
product review → AgenticFlywheel/prompts/PLAN_PRODUCT_REVIEW.md
eng review → AgenticFlywheel/prompts/PLAN_ENG_REVIEW.md
design review → AgenticFlywheel/prompts/PLAN_DESIGN_REVIEW.md
devex review → AgenticFlywheel/prompts/PLAN_DEVEX_REVIEW.md
autoplan → AgenticFlywheel/prompts/AUTOPLAN.md
prelanding review → AgenticFlywheel/prompts/PRELANDING_REVIEW.md
implementation audit, audit this AIP, run AIP audit → AgenticFlywheel/prompts/IMPLEMENTATION_AUDIT.md
save context → AgenticFlywheel/prompts/CONTEXT_SAVE.md
resume context or restore context → AgenticFlywheel/prompts/CONTEXT_RESTORE.md
qa → AgenticFlywheel/prompts/QA.md
ship → AgenticFlywheel/prompts/SHIP.md
guard mode → AgenticFlywheel/prompts/GUARD_MODE.md

Read the full file on GitHub · 63 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.

yesterday First seen · 63 lines · 962 tokens per session scan A fb9d1819c4df

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository RobLovesTech/AgenticFlyWheel (2 stars, last pushed 3mo ago), licensed MIT. It adds 962 tokens to every session, about $0.0048 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.

cursorrules

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

AgenticFlywheel Framework Integration

Canonical Sources

Context Gathering (Automatic)

Natural Command Routing

What this file has done since we first saw it

Other cursor rules, from other repositories

angular-20

dev-standard

typescript

coolify-ai-docs

python_lib

specs