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/jakerains/citrusrules/todo-trackinggit clone --depth 1 https://github.com/jakerains/CitrusRulesWhat 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 | $0.00033 | $0.02016 |
| Opus 5 | $0.00016 | $0.01008 |
| Sonnet 5 | $0.00007 | $0.00403 |
| Haiku 4.5 | $0.00003 | $0.00202 |
Grade A, and why
TODO-tracking 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.
How it starts
The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
description: TODO Tracking System - Automatically create and maintain TODO files for features and tasks globs:
- "**/*.{js,jsx,ts,tsx,py,go,rs,java,c,cpp,cs,rb,php,swift,kt,scala,r,m,dart,lua,jl,ex,clj,hs,ml,fs,v,vb,sql,sh,ps1,yaml,yml,json,xml,html,css,scss,sass,less,md,mdx,vue,svelte}"
- "**/TODO/*.md"
TODO Tracking System
A system for creating and maintaining TODO files that document the step-by-step process of implementing features, similar to Claude Code's checkpoint system.
content: |
TODO Tracking System Instructions
When /TODO is detected or this rule is relevant, follow these guidelines:
1. TODO File Creation
When starting a new feature or task:
- Create a file in
./TODO/directory named:YYYY-MM-DD_<task-name>.md - Use kebab-case for task names (e.g.,
2024-01-15_user-authentication-system.md) - If TODO directory doesn't exist, create it first
2. TODO File Structure
Each TODO file should follow this template:
# TODO: [Task Name]
**Created:** [Date]
**Status:** 🔄 In Progress | ✅ Complete | ⏸️ Paused | ❌ Blocked
**Priority:** 🔴 High | 🟡 Medium | 🟢 Low
**Related Files:** [List key files that will be modified]
**Issue/Ticket:** #[number] (if applicable)
## Overview
[Brief description of what we're implementing]
## Success Criteria
- [ ] [Specific measurable outcome 1]
- [ ] [Specific measurable outcome 2]
- [ ] [Specific measurable outcome 3]
## Dependencies
[Feature Name] ├── [Component 1] ✅ ├── [Component 2] 🔄 │ ├── [Subcomponent 2.1] ✅ │ └── [Subcomponent 2.2] ⏳ └── [Component 3] ⏳
## Implementation Steps
### Step 1: [Step Name] ✅
**Status:** Complete
What we did:
- [Action taken]
- [Files modified]
- [Key decisions made]
```[language]
// Code snippet showing the implementation
✓ Checkpoint: [What works at this point]
Commit: [hash] - "[commit message]"
Step 2: [Step Name] 🔄
Status: In Progress
What we're doing:
- [Current action]
- [Expected outcome]
Blockers: [Any issues encountered]
Step 3: [Step Name] ⏳
Status: Pending
What we need to do:
- [Planned action]
- [Dependencies]
Error Log
Error 1: [Date]
Error: [Error message]
Context: [Where it occurred]
Solution: [How it was fixed]
Prevention: [How to avoid in future]
Notes & Decisions
- [Date]: [Important decision or note]
- [Date]: [Why we chose approach A over B]
- [Date]: [Architectural decision]
Code Snippets & Solutions
[Problem/Feature Name]
// Reusable code solution
Why this works: [Explanation]
Next Session
When returning to this task:
- [First thing to check/do]
- [Second thing to check/do]
- [Continue from: specific file and line]
Pre-Completion Checklist
- All tests passing
- Code reviewed / AI-reviewed
- Documentation updated
- Edge cases handled
- Error handling implemented
- Security considerations addressed
Resources
- [Relevant documentation links]
- [Reference implementations]
- [Stack Overflow solutions that helped]
### 3. During Implementation
As you work through the task:
1. **Update status in real-time**:
- Mark steps as ✅ Complete, 🔄 In Progress, ❌ Blocked, or ⏳ Pending
- Remove time tracking - we work at AI speed!
2. **Document decisions**:
- Why did we choose approach A over B?
- What trade-offs did we make?
- What assumptions are we making?
3. **Create checkpoints**:
- After each significant step, note what's working
- Include git commit hashes for major checkpoints
- This helps with debugging and rolling back if needed
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 · 248 lines · 33 tokens per session scan A 8ec82eb2f315
TODO-tracking is a cursor rule published in the GitHub repository jakerains/CitrusRules (2 stars, last pushed 1y ago), licensed MIT. It adds 33 tokens to every session and 2,016 once invoked, about $0.0002 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 cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.