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 commands/walterra/claude-code-helpers/todogit clone --depth 1 https://github.com/walterra/claude-code-helpersWhat 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 | $0.00000 | $0.03389 |
| Opus 5 | $0.00000 | $0.01695 |
| Sonnet 5 | $0.00000 | $0.00678 |
| Haiku 4.5 | $0.00000 | $0.00339 |
Grade A, and why
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 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 — 343 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Todo Implementation Program
Structured workflow for implementing items from spec/todo.md. Work isolation in spec/todos/work/, completion tracking in spec/todos/done/. Enables concurrent work.
Overall guidance:
- CRITICAL: Follow all steps in the workflow! Do not miss executing any steps!
- CRITICAL: When refactoring, never assume that your code changes fix a problem without testing. Refactor using this loop: define goal -> code change -> test (use all available tools: logs/playwright mcp/screenshots etc.) -> if your testing doesn't satisfy the goal, move back to code change, repeat until done. if you're stuck, web research for solutions.
- Never mark off checkbox items as done when there are not fully completed or fixed!
- NEVER COMMIT OR PUSH: Agent must NEVER run git commit or git push commands. Only the USER commits/pushes changes.
Inputs
spec/todo.md - User's todo list (free form, any format):
- Add dark mode toggle to settings
- Should persist across sessions
- Use system preference as default
Fix memory leak in WebSocket handler
See issue #123
spec/project-description.md - Project context and commands (auto-generated, user-editable):
CRITICAL: always read spec/project-description.md for context.
# Project: Claude Code notifications
Shows system notifications when Claude Code sessions need user input.
TypeScript/Swift CLI tool with macOS daemon.
## Features
- System tray notifications
- Session monitoring
- macOS integration
## Commands
- **Check**: `npm run check`
- **Test**: `npm test`
- **Build**: `npm run build`
## Structure
src/cli.ts # CLI entry
src/mac/daemon.swift # Menu bar app
src/notifications.ts # Core logic
State
CRITICAL: Always keep the work items in sync in task.md in sync with your todos. Task completion requires ALL success criteria to be met.
ABSOLUTE RULE FOR TASK COMPLETION:
- NEVER mark any task item as [x] completed unless it is ABSOLUTELY, VERIFIABLY complete
- If ANY part of a task fails, produces errors, or doesn't work as specified, it MUST remain [ ] incomplete
- "Implemented" ≠ "Working" - only mark complete when functionality is verified working
- If you say "SUCCESS CRITERIA NOT MET" anywhere, NO related items can be marked [x] completed
- When in doubt, keep items unchecked [ ] - it's better to under-report progress than over-report
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 · 343 lines · 0 tokens per session scan A 88bb207536e2
todo is a command published in the GitHub repository walterra/claude-code-helpers (5 stars, last pushed 1y ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 3,389 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 2026-08-31.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.