A rule set for Claude that always requires Yarn for package management, end-to-end tests before implementation, verification afterward, and feature documentation in README.md.

Use it to guide Claude while adding features, running end-to-end tests, checking the result, and documenting changes.

It gives development tasks a fixed workflow and keeps the project documentation updated.

always-rule — Cursor rule by ranyitz

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/ranyitz/aicm/always-rule

Clone the repo

git clone --depth 1 https://github.com/ranyitz/aicm

Per session 5 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 43 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.

Model	Per session	Once invoked
Fable 5	$0.00005	$0.00043
Opus 5	$0.00003	$0.00022
Sonnet 5	$0.00001	$0.00009
Haiku 4.5	$0.00001	$0.00004

Measured 2d ago against content hash 4181e4b59957, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

always-rule 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.

tests/fixtures/claude-basic/rules/always-rule.mdc · 8 lines

What it actually says

Use yarn for package management
Development workflow: e2e tests → implementation → verification
Document all features in README.md

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.

2d ago First seen · 8 lines · 5 tokens per session scan A 4181e4b59957

Subscribe to this mod's changes

always-rule is a cursor rule published in the GitHub repository ranyitz/aicm (36 stars, last pushed 5mo ago), licensed MIT. It adds 5 tokens to every session and 43 once invoked, about $0.0000 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.

E2E testing Testing

always-rule

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other cursor rules, from other repositories

ui-testing

maestro-device-selection

webdriver-management

050-testing

local-compose-db-lifecycle-for-web-tests

cypress-e2e-testing-cursorrules-prompt-file