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 zeenie-ai/OpenCompany --skill google-tasks-skillgit clone --depth 1 https://github.com/zeenie-ai/OpenCompanyWrote 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/zeenie-ai/opencompany/google-tasks-skill)<a href="https://agentmods.dev/skills/zeenie-ai/opencompany/google-tasks-skill"><img src="https://agentmods.dev/badge/skills/zeenie-ai/opencompany/google-tasks-skill/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/zeenie-ai/opencompany/google-tasks-skill"><img src="https://agentmods.dev/badge/skills/zeenie-ai/opencompany/google-tasks-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00025 | $0.01161 |
| Opus 5 | $0.00013 | $0.00580 |
| Sonnet 5 | $0.00005 | $0.00232 |
| Haiku 4.5 | $0.00003 | $0.00116 |
Grade A, and why
google-tasks-skill 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 12d 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Tasks Skill
Manage Google Tasks - create, list, and complete tasks.
Tool: google_tasks
Consolidated Google Tasks tool with operation parameter.
Operations
| Operation | Description | Required Fields |
|---|---|---|
create |
Create a new task | title |
list |
List tasks from a list | (none, defaults to @default) |
complete |
Mark task as completed | task_id |
update |
Update an existing task | task_id |
delete |
Delete a task | task_id |
create - Create a new task
| Field | Type | Required | Description |
|---|---|---|---|
| operation | string | Yes | Must be "create" |
| title | string | Yes | Task title |
| notes | string | No | Task notes/description |
| due_date | string | No | Due date (ISO 8601 or YYYY-MM-DD) |
| tasklist_id | string | No | Task list ID (default: @default) |
Example - Simple task:
{
"operation": "create",
"title": "Review quarterly report"
}
Example - Task with details:
{
"operation": "create",
"title": "Submit expense report",
"notes": "Include receipts for conference travel",
"due_date": "2024-02-15"
}
list - List tasks
| Field | Type | Required | Description |
|---|---|---|---|
| operation | string | Yes | Must be "list" |
| tasklist_id | string | No | Task list ID (default: @default) |
| show_completed | boolean | No | Include completed tasks (default: false) |
| show_hidden | boolean | No | Include hidden tasks (default: false) |
| max_results | integer | No | Maximum results (default: 100) |
Example - List pending tasks:
{
"operation": "list",
"show_completed": false,
"max_results": 50
}
complete - Mark task as completed
| Field | Type | Required | Description |
|---|---|---|---|
| operation | string | Yes | Must be "complete" |
| task_id | string | Yes | Task ID to complete |
| tasklist_id | string | No | Task list ID (default: @default) |
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.
- 12d ago First seen · 170 lines · 25 tokens per session scan A 6200bcfca99a
google-tasks-skill is a skill published in the GitHub repository zeenie-ai/OpenCompany (880 stars, last pushed 2d ago), licensed MIT. It adds 25 tokens to every session and 1,161 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 2026-08-30.
Other skills, from other repositories
gh-issues
Fetch GitHub issues, select candidates, spawn background fix agents, open PRs, and optionally process PR review comments.
notion
Notion CLI/API for pages, Markdown content, data sources, files, comments, search, Workers, and raw API calls.
taskflow-inbox-triage
Preview synthetic inbox routing with a real TaskFlow approval pause, and identify the adapters needed for live triage.
taskflow
Run approval-gated workflows with durable TaskFlow state; distinguish workflow execution from linking real detached tasks.
things-mac
Add, update, list, search, or inspect Things 3 todos, inbox, today, projects, areas, and tags on macOS.
lobster
Lobster executes multi-step workflows with approval checkpoints. Use it when.