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.
npx agentmods add rules/wellapp-ai/well/initgit clone --depth 1 https://github.com/WellApp-ai/WellWhat 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 | $0.00013 | $0.01413 |
| Opus 5 | $0.00006 | $0.00707 |
| Sonnet 5 | $0.00003 | $0.00283 |
| Haiku 4.5 | $0.00001 | $0.00141 |
Grade A, and why
init 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.
How it starts
The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Init Mode
Use this mode to start a new feature from a clean slate.
Trigger Keywords
"init", "start feature", "new branch", "begin work on", "pick up task"
The Flow
- Resume Detection - Check if branch has open PR with comments
- Clean Slate - Ensure working directory is clean
- Sync - Reset to latest develop
- Context - Fetch task from Notion (including linked pages)
- Branch - Create feature branch, update Notion
- ASK Handoff - Present summary, wait for user to confirm ASK mode
Phase Checklist
Phase 0: Resume Detection
Before clean slate, check if resuming existing work:
- Check current branch:
git branch --show-current - If NOT on develop, check for open PR:
gh pr view --json number,state,url,title - If PR exists with comments/reviews, fetch feedback:
gh pr view --json comments,reviewsgh api repos/{owner}/{repo}/pulls/{number}/comments
If PR with feedback exists → Skip to Resume Flow below If no PR or no feedback → Continue to Phase 1
Resume Flow
When an open PR with review comments is detected:
Present to user:
Resume: PR Review Feedback
Branch: [branch-name] PR: #[number] - [title] URL: [PR URL]
Review Comments
| Reviewer | Location | Comment |
|---|---|---|
| @reviewer | file.ts:L42 |
"Comment text..." |
Summary of Requested Changes
- [Bullet point for each actionable comment]
Would you like me to create a plan to address these comments?
Say "yes" to create a fix plan, or "skip" to continue with normal init.
Wait for user confirmation before proceeding.
Phase 1: Clean Slate
- Check for changes:
git status --porcelain - If dirty, stash:
git stash push -m "pre-init: $(git branch --show-current)" - Confirm clean:
git statusshows nothing to commit
Phase 2: Sync with Develop
- Fetch:
git fetch origin develop - Switch:
git checkout develop - Reset:
git reset --hard origin/develop - Clear caches:
npm run clean - Install:
npm install - Typecheck:
npm run typecheck
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 · 209 lines · 13 tokens per session scan A a8afca37b734
init is a cursor rule published in the GitHub repository WellApp-ai/Well (341 stars, last pushed 25d ago), licensed MIT. It adds 13 tokens to every session and 1,413 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 2026-08-30.
Other cursor rules, from other repositories
upgrade-tests
// ✅ CORRECT: Upgrade package pattern await using ctx = testReactResource(appRouter, { server: { // server configuration }, client(opts) { return { links: [ httpLink({ url: opts.httpUrl, // client configuration }), ], }; }, }).
test-running
When running tests, use the --watch false flag to avoid watch mode.
middleware
When you need create a middleware to protect some page of Next.js app.
memory
Establishes a persistent memory protocol for capturing and retrieving knowledge, including storage strategies, context retrieval, and proactive memory management for continuous learning.
taskmaster
Comprehensive reference for Taskmaster MCP tools and CLI commands.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.