Borrowing it
Nothing to install: this file belongs to vguleaev/cursor-todo-prompt-kit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vguleaev/cursor-todo-prompt-kit/main/.cursor/skills/ct-init-todo/SKILL.mdgit clone --depth 1 https://github.com/vguleaev/cursor-todo-prompt-kitWrote 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.
[](https://agentmods.dev/skills/vguleaev/cursor-todo-prompt-kit/ct-init-todo)<a href="https://agentmods.dev/skills/vguleaev/cursor-todo-prompt-kit/ct-init-todo"><img src="https://agentmods.dev/badge/skills/vguleaev/cursor-todo-prompt-kit/ct-init-todo/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/vguleaev/cursor-todo-prompt-kit/ct-init-todo"><img src="https://agentmods.dev/badge/skills/vguleaev/cursor-todo-prompt-kit/ct-init-todo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00022 | $0.01051 |
| Opus 5 | $0.00011 | $0.00526 |
| Sonnet 5 | $0.00004 | $0.00210 |
| Haiku 4.5 | $0.00002 | $0.00105 |
Grade A, and why
ct-init-todo 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ct-init-todo
For the given feature, create a TODO.md file in the root of the project.
TODO.md file Rules
- Generate as many tasks as you need to complete the feature.
- Each task must have a unique task ID.
- Task ID must be in the format of
CT-<number>. - You must use the following statuses:
✅ DONE,🔲 TODO. - You muse use prefix
CT-for the task ID. - Each task must have name, description and acceptance criteria.
- Add helpful notes which are common for all tasks at the end of the file.
YOU MUST USE THE FOLLOWING TEMPLATE:
# TODO: {{FEATURE_NAME}}
{{FEATURE_DESCRIPTION}}
## Progress Tracker
| Ticket | Description | Status |
| ------ | --------------- | ------------ |
| CT-1 | {{TASK_1_NAME}} | {{STATUS_1}} |
| CT-2 | {{TASK_2_NAME}} | {{STATUS_2}} |
## Tasks
#### CT-1: {{TASK_1_NAME}}
**Description:**
{{TASK_1_DESCRIPTION}}
**Acceptance Criteria:**
- [ ] {{ACCEPTANCE_CRITERIA_1}}
- [ ] {{ACCEPTANCE_CRITERIA_2}}
- [ ] {{ACCEPTANCE_CRITERIA_3}}
- [ ] {{ACCEPTANCE_CRITERIA_4}}
---
#### CT-2: {{TASK_2_NAME}}
**Description:**
{{TASK_2_DESCRIPTION}}
**Acceptance Criteria:**
- [ ] {{ACCEPTANCE_CRITERIA_1}}
- [ ] {{ACCEPTANCE_CRITERIA_2}}
- [ ] {{ACCEPTANCE_CRITERIA_3}}
---
## Notes
- {{NOTE_1}}
- {{NOTE_2}}
- {{NOTE_3}}
Find below complete example of a TODO.md file:
# TODO: Expenses Tracker Backend
Implement insertion of a new expense into the database for our expenses tracker.
## Progress Tracker
| Ticket | Description | Status |
| ------ | ---------------------- | ------- |
| CT-1 | CDK Backend Stack | ✅ DONE |
| CT-2 | Deploy Lambda Handlers | ✅ DONE |
| CT-3 | Custom Domain for API | ✅ DONE |
| CT-4 | API Gateway Auth | 🔲 TODO |
## Tasks
#### CT-1: Create CDK Backend Stack for Lambda + DynamoDB
**Description:**
Create a new CDK stack (`backend-stack.ts`) that provisions:
- DynamoDB table for expenses with `id` as partition key and `userId-index` GSI
- Lambda functions for expense CRUD operations
- API Gateway REST API with proper CORS configuration
- IAM roles and permissions for Lambda to access DynamoDB
**Acceptance Criteria:**
- [x] DynamoDB table created with proper indexes
- [x] Lambda functions deployed for list/create expenses
- [x] API Gateway configured with routes
- [x] Stack outputs API URL
---
#### CT-2: Deploy Expense Lambda Handlers
**Description:**
Bundle and deploy existing Lambda handlers (`create.ts`, `list.ts`) to AWS via CDK. Ensure environment variables are properly configured.
**Acceptance Criteria:**
- [x] Create expense Lambda deployed
- [x] List expenses Lambda deployed
- [x] Environment variables set (EXPENSES_TABLE_NAME)
- [x] Handlers return proper responses
---
#### CT-3: Add Custom Domain for API Gateway
**Description:**
Configure custom domain `api.expenses.example.com` for API Gateway. Reuse existing certificate if it supports wildcards, or update certificate to include the API subdomain.
**Acceptance Criteria:**
- [x] Check if existing certificate supports `*.expenses.example.com` or `api.expenses.example.com`
- [x] If not, request new/updated certificate with wildcard support
- [x] Add custom domain to API Gateway in CDK
- [x] Created DNS record for `api.expenses.example.com`
- [x] API accessible via `https://api.expenses.example.com`
---
#### CT-4: Configure API Gateway with Clerk Auth Integration
**Description:**
Set up API Gateway to validate Clerk JWT tokens. Configure Lambda authorizer or pass user ID from Clerk session to backend.
**Acceptance Criteria:**
- [ ] API Gateway validates auth headers
- [ ] User ID extracted from Clerk token
- [ ] Unauthorized requests return 401
---
## Notes
- Backend handlers already exist in `/backend/src/handlers/expenses/`
- Auth utility exists in `/backend/src/lib/auth.ts`
- Frontend uses Clerk for authentication
- DynamoDB requires `userId-index` GSI for listing user's expenses
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.
- 8d ago First seen · 159 lines · 22 tokens per session scan A acbba743ad8a
ct-init-todo is a skill published in the GitHub repository vguleaev/cursor-todo-prompt-kit (3 stars, last pushed 6mo ago), licensed MIT. It adds 22 tokens to every session and 1,051 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 2026-08-31.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
remove
Remove a deployed framework or addon from the current workspace.