00-hard-rules

00-hard-rules is a cursor rule for coding agents from WellApp-ai/Well. It costs 1,177 tokens per session, scanned A, original, MIT.

A single rulebook containing the required and forbidden behaviors for a coding project. It defines workflows for tasks such as starting work, investigating, planning, committing, and opening a pull request.

In plain words
What is it for?
Use it to enforce project-wide rules, select the correct workflow from a user request, show progress in phases, and pause for confirmation at required checkpoints.
Why use it?
It prevents different rule files from contradicting one another and makes sure important workflow steps are not skipped. Trigger words require the matching workflow to be read and followed before action begins.

Cursor rule

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/wellapp-ai/well/00-hard-rules
Clone the repo
git clone --depth 1 https://github.com/WellApp-ai/Well

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 00-hard-rules

README.md
[![agentmods](https://agentmods.dev/badge/rules/wellapp-ai/well/00-hard-rules.svg)](https://agentmods.dev/rules/wellapp-ai/well/00-hard-rules)
Your own site
<a href="https://agentmods.dev/rules/wellapp-ai/well/00-hard-rules"><img src="https://agentmods.dev/badge/rules/wellapp-ai/well/00-hard-rules.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,177 This file is loaded in full into every session.
When invoked 1,177 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 $0.01177 $0.01177
Opus 5 $0.00589 $0.00589
Sonnet 5 $0.00235 $0.00235
Haiku 4.5 $0.00118 $0.00118

Measured 3d ago against content hash 75d868f8c992, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

00-hard-rules 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 3d 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/rules/00-hard-rules.mdc · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hard Rules (Canonical)

Mode Trigger Enforcement (CRITICAL)

When ANY mode trigger keyword is detected in user message, you MUST:

  1. STOP - Do NOT take any action yet
  2. READ the full mode file using the Read tool
  3. OUTPUT confirmation: "Following [Mode] workflow from .cursor/rules/modes/[mode].mdc..."
  4. EXECUTE phases in order with visible checkboxes
  5. WAIT at each gate for user confirmation

Trigger Keywords → Mode File:

Keywords Mode File to Read
"init", "start feature", "new branch", "begin work", "pick up" .cursor/rules/modes/init.mdc
"ask", "explore", "analyze", "investigate" .cursor/rules/modes/ask.mdc
"plan", "design", "architect" .cursor/rules/modes/plan.mdc
"commit", "prepare commit" .cursor/rules/modes/commit.mdc
"push PR", "create PR", "open PR" .cursor/rules/modes/push-pr.mdc

Required Output Format:

Detected mode trigger: "[keyword]"
Following [Mode] workflow from `.cursor/rules/modes/[mode].mdc`...

## Phase [N]: [Name]
- [ ] Step 1
- [ ] Step 2
...

NEVER skip reading the mode file. NEVER act on a trigger keyword without following the full workflow. NEVER use the summary from 03-shared.mdc instead of the full mode file.

TypeScript

  • Strict mode enabled
  • NO any type - use unknown or proper generics
  • Run npm run typecheck before every commit

Styling

  • Tailwind utilities ONLY
  • NO CSS modules, styled-components, or inline styles
  • NO arbitrary values (px-[13px]) - use design tokens only

Component Size

  • Target: <150 lines per component
  • Warning: 150-200 lines (plan to split)
  • Violation: >200 lines (MUST split before adding features)

API Integration

  • 3-layer pattern: ApiClient → Service → Query Hook
  • NO direct fetch calls in components
  • NO hardcoded API URLs
  • Use API_CONFIG.BASE_URL (wraps NEXT_PUBLIC_WELL_API_BASE_URL)

Reuse First (CRITICAL)

Before creating ANYTHING new, search for existing:

Read the full file on GitHub · 137 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. 3d ago First seen · 137 lines · 1,177 tokens per session scan A 75d868f8c992

Subscribe to this mod's changes

00-hard-rules is a cursor rule published in the GitHub repository WellApp-ai/Well (340 stars, last pushed 27d ago), licensed MIT. It adds 1,177 tokens to every session, about $0.0059 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.