create-todos

create-todos is a command for coding agents from brennercruvinel/CCPlugins. It costs 0 tokens per session (463 once invoked), scanned A, original, MIT.

A command for adding TODO comments to code based on recent work, such as test failures, security findings, review feedback, or suggested improvements.

In plain words
What is it for?
Use it to inspect project conventions, find suitable code locations, and create categorized TODOs with actionable context.
Why use it?
It turns issues discovered during development into specific, well-placed reminders that match the project's existing comment style.

Command

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 commands/brennercruvinel/ccplugins/create-todos
Clone the repo
git clone --depth 1 https://github.com/brennercruvinel/CCPlugins

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 create-todos

README.md
[![agentmods](https://agentmods.dev/badge/commands/brennercruvinel/ccplugins/create-todos.svg)](https://agentmods.dev/commands/brennercruvinel/ccplugins/create-todos)
Your own site
<a href="https://agentmods.dev/commands/brennercruvinel/ccplugins/create-todos"><img src="https://agentmods.dev/badge/commands/brennercruvinel/ccplugins/create-todos.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 463 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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00463
Opus 5 $0.00000 $0.00231
Sonnet 5 $0.00000 $0.00093
Haiku 4.5 $0.00000 $0.00046

Measured 4d ago against content hash b717da5d4ed2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-todos 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 4d 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.

commands/create-todos.md · 60 lines

What it actually says

Create Smart TODOs

I'll analyze recent operations and create contextual TODO comments in your code.

First, let me understand your project standards:

  • Read README.md for project conventions
  • Read CONTRIBUTING.md for code style guidelines
  • Grep existing TODOs to match your format
  • Read documentation for technical context

I'll examine what just happened in our session:

  • Security scan findings that need fixes
  • Test failures requiring attention
  • Code review issues to address
  • Architecture improvements identified
  • Performance optimizations suggested

Using native tools to analyze context:

  • Grep tool to find related code sections
  • Read tool to understand implementation details
  • TodoWrite to track what TODOs I'm creating

For each TODO I'll:

  1. Find the exact location where it belongs
  2. Analyze surrounding code for context
  3. Create clear, actionable TODO comments
  4. Include priority and category markers

TODO Format Adaptation: I'll match your project's existing TODO style:

  • Check if you use categories like [Security] or (SECURITY)
  • Match comment style: //, #, /* */, etc.
  • Follow any ticket reference patterns your project uses
  • Respect line length limits from your linter

Smart Context References: I'll create TODOs that reference the source of the issue:

  • Security findings will reference the scan line number
  • Performance issues will include measured thresholds
  • Bug fixes will reference failing test locations
  • Refactoring needs will reference architectural patterns

I'll use intelligent placement:

  • Security TODOs near vulnerable code
  • Performance TODOs at bottleneck locations
  • Bug fixes where errors occur
  • Architecture TODOs at integration points

After creating TODOs, I'll ask: "How would you like to track these?"

  • Convert to GitHub issues with /todos-to-issues
  • Keep as code comments for gradual resolution
  • Generate summary report for team review

Important: I will NEVER:

  • Add "Generated by Claude" or AI attribution in TODOs
  • Create vague or non-actionable TODOs
  • Place TODOs in random locations
  • Overwhelm code with excessive comments

This creates a clear technical debt roadmap directly in your codebase.

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. 4d ago First seen · 60 lines · 0 tokens per session scan A b717da5d4ed2

Subscribe to this mod's changes

create-todos is a command published in the GitHub repository brennercruvinel/CCPlugins (2,780 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 463 tokens. 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.