Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/WadeWarren/gws-claude-pluginnpx agentmods add skills/wadewarren/gws-claude-plugin/gws-tasksWrote 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/wadewarren/gws-claude-plugin/gws-tasks)<a href="https://agentmods.dev/skills/wadewarren/gws-claude-plugin/gws-tasks"><img src="https://agentmods.dev/badge/skills/wadewarren/gws-claude-plugin/gws-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/wadewarren/gws-claude-plugin/gws-tasks"><img src="https://agentmods.dev/badge/skills/wadewarren/gws-claude-plugin/gws-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 | $0.00014 | $0.00720 |
| Opus 5 | $0.00007 | $0.00360 |
| Sonnet 5 | $0.00003 | $0.00144 |
| Haiku 4.5 | $0.00001 | $0.00072 |
Grade A, and why
gws-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 10d 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.
This is a copy
98% identical to gws-tasks — 5 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tasks (v1)
PREREQUISITE: Read
../gws-shared/SKILL.mdfor auth, global flags, and security rules. If missing, rungws generate-skillsto create it.
gws tasks <resource> <method> [flags]
API Resources
tasklists
delete— Deletes the authenticated user's specified task list. If the list contains assigned tasks, both the assigned tasks and the original tasks in the assignment surface (Docs, Chat Spaces) are deleted.get— Returns the authenticated user's specified task list.insert— Creates a new task list and adds it to the authenticated user's task lists. A user can have up to 2000 lists at a time.list— Returns all the authenticated user's task lists. A user can have up to 2000 lists at a time.patch— Updates the authenticated user's specified task list. This method supports patch semantics.update— Updates the authenticated user's specified task list.
tasks
clear— Clears all completed tasks from the specified task list. The affected tasks will be marked as 'hidden' and no longer be returned by default when retrieving all tasks for a task list.delete— Deletes the specified task from the task list. If the task is assigned, both the assigned task and the original task (in Docs, Chat Spaces) are deleted. To delete the assigned task only, navigate to the assignment surface and unassign the task from there.get— Returns the specified task.insert— Creates a new task on the specified task list. Tasks assigned from Docs or Chat Spaces cannot be inserted from Tasks Public API; they can only be created by assigning them from Docs or Chat Spaces. A user can have up to 20,000 non-hidden tasks per list and up to 100,000 tasks in total at a time.list— Returns all tasks in the specified task list. Doesn't return assigned tasks by default (from Docs, Chat Spaces). A user can have up to 20,000 non-hidden tasks per list and up to 100,000 tasks in total at a time.move— Moves the specified task to another position in the destination task list. If the destination list is not specified, the task is moved within its current list. This can include putting it as a child task under a new parent and/or move it to a different position among its sibling tasks. A user can have up to 2,000 subtasks per task.patch— Updates the specified task. This method supports patch semantics.update— Updates the specified task.
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.
- 10d ago First seen · 57 lines · 14 tokens per session scan A fb023b98f2cb
gws-tasks is a skill published in the GitHub repository WadeWarren/gws-claude-plugin (38 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 14 tokens to every session and 720 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to gws-tasks, differing in 5 lines, and is treated as a copy.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.