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 skills add xdg/xdg-claude --skill todo-plannergit clone --depth 1 https://github.com/xdg/xdg-claudeWrote 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/xdg/xdg-claude/todo-planner)<a href="https://agentmods.dev/skills/xdg/xdg-claude/todo-planner"><img src="https://agentmods.dev/badge/skills/xdg/xdg-claude/todo-planner/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/xdg/xdg-claude/todo-planner"><img src="https://agentmods.dev/badge/skills/xdg/xdg-claude/todo-planner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 3 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- high Prompt Injection · line 99 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 114 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00066 | $0.01407 |
| Opus 5.5 | $0.00026 | $0.00563 |
| Sonnet 5.5 | $0.00013 | $0.00281 |
| Haiku 4.5 | $0.00007 | $0.00141 |
Grade A, and why
todo-planner 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 1mo 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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TODO Planner
Overview
Create structured TODO.md files for tracking multi-phase implementation projects. The format emphasizes testability, verification, and phase dependencies to maintain context and ensure thorough execution.
Document Structure
A TODO.md file consists of these sections in order:
# Project Implementation Plan
[1-2 sentence description]
## Testing Philosophy
[Testing approach preamble - re-injected for context retention]
## Verification Checklist
[Pre-commit checklist - re-injected for context retention]
## Dependencies Between Phases
[ASCII diagram showing phase relationships]
---
## Phase N: Title
[Phase description]
### N.1 Sub-phase title
- [x] Completed task
- [ ] Pending task
- [ ] **Test**: Explicit test task
---
## Future Phases (Deferred)
[Items explicitly out of scope for now]
Nesting subphases
Subphases may be nested, if the complexity of a phase is high. Number them hierarchically: x.y or x.y.z or x.y.z.a, a necessary. The scope of a subphase should be work that can be completed in a single agent session and would logically make sense as an atomic commit -- a single, logical unit of change.
Testing Philosophy Preamble
Include a Testing Philosophy section near the top. This section is critical for context retention - when working on later phases, this preamble reminds the agent of testing expectations.
Template:
## Testing Philosophy
- **Automated tests for business logic**: [specific areas like store operations, API handlers]
- **Playwright tests for UI interactions**: [specific areas like drag-drop, visual behavior]
- **Manual tests for subjective UI experience**: [specific areas that require human input]
- **Factor code for testability**: Interfaces for backends, dependency injection
- **[Language] tests**: [framework specifics, e.g., "Use `testing` with `httptest` for handlers"]
- **[Frontend] tests**: [framework specifics, e.g., "Vitest for component logic"]
Test what new code changes. Don't revalidate behaviors already tested in earlier commits. E.g. browser tests
are for layout, controls, navigation, storage, not API contracts backend tests already cover.
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.
- 1mo ago Changed · +4 lines a3f0e3986470
- 2mo ago First seen · 197 lines · 66 tokens per session scan A a27f8730a36f
todo-planner is a skill published in the GitHub repository xdg/xdg-claude (20 stars, last pushed 6d ago), licensed Apache-2.0. It adds 66 tokens to every session and 1,407 once invoked, about $0.0003 per session on Opus 5.5. 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.
todo-planner compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| todo-plannerxdg/xdg-claude | Skill | 20 | 6d ago | Apache-2.0 | A | 66 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |