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 Teamwork/mcp --skill teamwork-workflowsgit clone --depth 1 https://github.com/Teamwork/mcpWrote 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/teamwork/mcp/teamwork-workflows)<a href="https://agentmods.dev/skills/teamwork/mcp/teamwork-workflows"><img src="https://agentmods.dev/badge/skills/teamwork/mcp/teamwork-workflows/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/teamwork/mcp/teamwork-workflows"><img src="https://agentmods.dev/badge/skills/teamwork/mcp/teamwork-workflows.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 | $0.00050 | $0.00700 |
| Opus 5.5 | $0.00020 | $0.00280 |
| Sonnet 5.5 | $0.00010 | $0.00140 |
| Haiku 4.5 | $0.00005 | $0.00070 |
Grade A, and why
teamwork-workflows 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 yesterday.
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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Teamwork.com workflows
Use the connected Teamwork.com MCP tools to complete the user's requested work. Discover the available tools and read their schemas before invoking them; tool availability depends on OAuth scopes, permissions, and the connected server. Do not assume a tool exists from its name alone.
Before retrieving data, determine whether the requested operation is supported by the available tools. If it is outside this connection's capabilities, explain that limitation without calling unrelated tools or substituting another action. A related record or workflow does not establish that the requested action is supported.
Find the right records
- Resolve the intended project, task, ticket, person, space, or conversation using available search/list tools. Reuse known IDs and links from context; ask a concise question only when multiple matches would change the action.
- Keep queries focused with supported filters. Respect pagination and server limits. State when a summary covers only some results; do not treat the first page as exhaustive.
- Read the selected record before updating it when its current state matters. Preserve fields outside the requested change.
Projects and time
Use the available Projects tools for projects, tasks, tasklists, milestones, comments, people, timers, timelogs, budgets, and planning. Resolve assignees and parent records before creating work. Use dates, time zones, durations, and status values as specified by the tool schema; clarify materially ambiguous time entries.
For workload questions, follow the tool's definition of capacity and working hours. Keep task workload and resource allocations separate rather than adding them together. Use count or summary tools when exposed and appropriate, instead of fetching every record solely to compute a total.
Desk
Use the available Desk tools to search tickets, inspect ticket details and history, and work with customers and supported ticket fields. Resolve inbox, status, priority, and assignee values using supported tools instead of inventing IDs. Distinguish a public reply from an internal note using the actual tool schema. Send a reply or message only when the user authorizes sending it; otherwise provide a draft.
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.
- yesterday First seen · 41 lines · 50 tokens per session scan A bc666a58368b
teamwork-workflows is a skill published in the GitHub repository Teamwork/mcp (27 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 700 once invoked, about $0.0002 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 2026-10-24.
Other skills, from other repositories
import-spreadsheet
Import rows from a CSV or Excel file into a Taskade project (leads, contacts, jobs, products, inventory), skip duplicates, and fill custom fields. Use when the user says "import this spreadsheet into Taskade", "add these leads to my CRM", "load this CSV into my app", or attaches a CSV or XLSX and names a Taskade…
app-report
Build a short status report from the user's Taskade projects (jobs, leads, invoices, tasks) and automations, with counts, what changed, what is overdue, which automations failed, and who owns it. Use when the user asks for "a weekly report", "status of my Taskade workspace", "how is my pipeline", "what is overdue"…
plan-new-app
Plan a new Taskade Genesis app from a business goal, create its data projects and its AI agent in Taskade, and write the build prompt for Taskade EVE. Use when the user says "build me an app in Taskade", "I need a CRM / client portal / booking system / dashboard", "plan a Taskade app", or describes a business process…
getting-started
Connect Taskade and show the user what they can do with it. Use when the user says "set up Taskade", "connect Taskade", "what can you do in Taskade", "what is in my Taskade workspace", or when a Taskade tool fails with a sign-in or plan error.
taskade
Use Taskade from any AI agent. Read and change a user's Taskade workspace (projects, tasks, AI agents and Taskade Genesis app files), and read and run automations, through the hosted Taskade MCP server. Use when the user mentions Taskade, a Taskade Genesis app, or asks to build an app, deploy an AI agent, automate a…
issue-management
Create, update, list and search GitHub issues and PRs, list a repository's labels, run milestones, and check for duplicates.