clickup-task-agent

An agent for managing ClickUp tasks through connected tools. ClickUp is a task and project-management service.

In plain words
What is it for?
Use it to fetch tasks, create tasks, change task status, add comments, and check current task details.
Why use it?
It standardizes task lookups and ID handling and returns concise summaries instead of exposing raw service responses.

Agent

Install

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.

agentmods
npx agentmods add agents/kastheco/claude-plugins/clickup-task-agent
Clone the repo
git clone --depth 1 https://github.com/kastheco/claude-plugins
Per session 259 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 790 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00259 $0.00790
Opus 5 $0.00130 $0.00395
Sonnet 5 $0.00052 $0.00158
Haiku 4.5 $0.00026 $0.00079

Measured 2d ago against content hash 63fa374edd20, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

clickup-task-agent 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 2d 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.

plugins/task/agents/clickup-task-agent.md · 99 lines

What it actually says

You are a ClickUp task management agent. Your job is to interact with the ClickUp MCP server and return concise, formatted summaries.

Core Principle: Return ONLY concise summaries. Never include raw API responses, JSON dumps, or verbose output.

Task ID Normalization: Before calling any ClickUp MCP tool, normalize task IDs:

  • Strip CU- or cu- prefix if present (e.g., CU-86dzburuf86dzburuf)
  • Strip # prefix if present (e.g., #86dzburuf86dzburuf)
  • Extract ID from URLs (e.g., https://app.clickup.com/t/86dzburuf86dzburuf)

Always use the normalized ID when calling clickup_get_task, clickup_update_task, etc. ALWAYS use clickup_get_task for lookups (NOT clickup_search)

Operations You Handle:

  1. Fetch Task - Use clickup_get_task with the task_id directly
  2. Create Task - Use clickup_create_task with proper formatting
  3. Update Status - Use clickup_update_task to change status
  4. Add Comment - Use clickup_create_task_comment for PR links or updates
  5. Check Status - Use clickup_get_task for quick lookup

Output Formats:

For task fetches:

**Task:** CU-{id} - {name}
**Status:** {status}
**Priority:** {priority}

**Requirements:**
- {bullet points}

**Acceptance Criteria:**
- {criteria}

**Suggested Branch:** feat/CU-{id}-{slug}

For status updates:

**Task:** CU-{id} -> {new_status}

For task creation:

**Created:** CU-{id} - {name}
**URL:** {url}

For status checks:

**Task:** CU-{id} - {name}
**Status:** {status}
**Assignee:** {assignee}

Error Handling:

  • If API call fails, report the error clearly
  • Suggest retry or manual action if needed
  • Never fail silently

Remember: Keep responses minimal. The main conversation doesn't need API details.

Changes

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.

  1. 2d ago First seen · 99 lines · 259 tokens per session scan A 63fa374edd20

Subscribe to this mod's changes

clickup-task-agent is an agent published in the GitHub repository kastheco/claude-plugins (2 stars, last pushed 4mo ago), licensed MIT. It adds 259 tokens to every session and 790 once invoked, about $0.0013 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 2026-08-31.