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 IceWhaleTech/ZimaOS-Blue --skill tasksgit clone --depth 1 https://github.com/IceWhaleTech/ZimaOS-BlueWrote 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/icewhaletech/zimaos-blue/tasks)<a href="https://agentmods.dev/skills/icewhaletech/zimaos-blue/tasks"><img src="https://agentmods.dev/badge/skills/icewhaletech/zimaos-blue/tasks/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/icewhaletech/zimaos-blue/tasks"><img src="https://agentmods.dev/badge/skills/icewhaletech/zimaos-blue/tasks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00040 | $0.00819 |
| Opus 5 | $0.00020 | $0.00409 |
| Sonnet 5 | $0.00008 | $0.00164 |
| Haiku 4.5 | $0.00004 | $0.00082 |
Grade A, and why
tasks 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 9d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tasks
Use the external things binary via blue exec to read and update a real Things 3 task list on macOS.
Setup
Install the CLI if needed:
blue exec command='GOBIN=/opt/homebrew/bin go install github.com/ossianhempel/things3-cli/cmd/things@latest'
Sanity-check the install:
blue exec command='things --help'
If database reads fail, grant Full Disk Access to the calling app (for example Terminal or your IDE).
Optional environment:
THINGSDBor--dbto point at a specificThingsData-*folderTHINGS_AUTH_TOKENto avoid passing--auth-tokenfor update operations
Task Routing
| User Intent | Action |
|---|---|
| Read inbox/today/upcoming/search/projects in Things 3 | blue exec command='things ...' |
| Add or update real tasks in the user's Things database | blue exec command='things add ...' / blue exec command='things update ...' |
| User wants a reminder/alert notification | Use reminder, not tasks |
| User wants recurring command automation | Use scheduler, not tasks |
| User only needs an in-chat checklist or plan | Prefer normal chat output or the plan skills, not tasks |
Command Usage
Read from Things:
blue exec command='things inbox --limit 50'
blue exec command='things today'
blue exec command='things upcoming'
blue exec command='things search "query"'
blue exec command='things projects'
Add tasks:
blue exec command='things --dry-run add "Title"'
blue exec command='things add "Title" --notes "..." --when today --deadline 2026-01-02'
blue exec command='things add "Book flights" --list "Travel"'
blue exec command='things add "Call dentist" --tags "health,phone"'
Update tasks (auth token required):
blue exec command='things search "milk" --limit 5'
blue exec command='things update --id <UUID> --auth-token <TOKEN> --completed'
blue exec command='things update --id <UUID> --auth-token <TOKEN> --notes "New notes"'
Notes
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.
- 9d ago First seen · 112 lines · 40 tokens per session scan A 2d5677b5e1bf
tasks is a skill published in the GitHub repository IceWhaleTech/ZimaOS-Blue (25 stars, last pushed 4mo ago), licensed MIT. It adds 40 tokens to every session and 819 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 2026-08-30.
Other skills, from other repositories
linear
Manage Linear issues, projects, and teams via the GraphQL API. Create, update, search, and organize issues. Uses API key auth (no OAuth needed). All operations via curl — no dependencies.
notion
Notion API for creating and managing pages, databases, and blocks via curl. Search, create, update, and query Notion workspaces directly from the terminal.
commonly
You are a member of a Commonly workspace — a shared space where humans and AI agents from any origin collaborate in pods (chat rooms with memory). Use this whenever you are connected to Commonly via the commonly MCP tools: to read what's happening, post, remember things across sessions, react, DM other agents, and…
google-tasks-skill
Create, list, and complete Google Tasks. Supports task lists, due dates, and notes.
task-manager
Coordinate durable team tasks by assigning connected teammates, reviewing results, and accepting, retrying, reassigning, or cancelling work.
subagent-orchestration
Coordinate connected subagents through durable Task Manager assignments, bounded parallel execution, review, retry, reassignment, and acceptance.