pickle-clickup

pickle-clickup is a skill for Claude Code from adityaarsharma/pickle. It costs 97 tokens per session (23,856 once invoked), scanned B, original, MIT.

A ClickUp task-finding assistant that scans followed channels, direct messages, and group messages for work requiring your action or follow-up on delegated work.

In plain words
What is it for?
Use it to find actionable items in ClickUp and create prioritised tasks with the original conversation context.
Why use it?
It gathers requests and outstanding follow-ups from scattered ClickUp conversations so they are less likely to be missed.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: reads .claude/ paths; mentions subagents; mentions Claude Code.

Good fit Use it to find actionable items in ClickUp and create prioritised tasks with the original conversation context.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/adityaarsharma/pickle/pickle-clickup
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.

Any agent
npx skills add adityaarsharma/pickle --skill pickle-clickup
Clone the repo
git clone --depth 1 https://github.com/adityaarsharma/pickle

Made for: Claude Code.

Wrote 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.

agentmods badge for pickle-clickup

README.md
[![agentmods](https://agentmods.dev/badge/skills/adityaarsharma/pickle/pickle-clickup.svg)](https://agentmods.dev/skills/adityaarsharma/pickle/pickle-clickup)
Your own site
<a href="https://agentmods.dev/skills/adityaarsharma/pickle/pickle-clickup"><img src="https://agentmods.dev/badge/skills/adityaarsharma/pickle/pickle-clickup.svg" alt="Measured on agentmods" height="20"></a>
Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 23,856 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00097 $0.23856
Opus 5 $0.00048 $0.11928
Sonnet 5 $0.00019 $0.04771
Haiku 4.5 $0.00010 $0.02386

Measured 7d ago against content hash cbd434fc7afc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

pickle-clickup scanned grade B with 1 finding 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 7d 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.

Enumerates other installed skillsmediumAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

1. Before writing the new file, clean up old scratch: `find ~/.claude/skills/pickle-clickup/.scratch -name 'scan-*.json' -mtime +7 -delete 2>/dev/null` — removes scratch files older than 7 days so daily runs don't accumu
pickle-clickup/SKILL.md · 1,434 lines

How it starts

The opening of the file, as written. The whole thing — 1,434 lines — stays where its author put it; the contents beside it link to each section on GitHub.

pickle-clickup 🥒

Part of Pickle · Built by Aditya Sharma

You are the pickle-clickup agent for the authenticated ClickUp user. Pickle is a two-ecosystem productivity skill — this file handles the ClickUp ecosystem only. (Slack is handled by pickle-slack, completely separate.)

ECOSYSTEM RULE — ABSOLUTE:

  • This skill uses ONLY ClickUp tools (clickup_*). No Slack tools, ever, including at notification time.
  • ClickUp items → ClickUp personal task board. Never create Slack messages or list entries from ClickUp data.
  • Notifications → ClickUp deadline task ONLY (the 🔔 hack). NEVER call slack_*, slack_reminder_add, or any pickle-slack-mcp tool — not even for the completion ping. Slack gets its own notification only when /pickle-slack runs.
  • ClickUp data never leaves the ClickUp ecosystem.

ABSOLUTE SCANNING MANDATE — NEVER SKIP THESE

Every run MUST scan ALL of the following. No source is optional. No budget constraint justifies skipping a DM, a task comment, or a threaded reply. Missing any of these is a bug, not a trade-off.

Source Scan Rule Why it cannot be skipped
All DMs I'm in (is_dm: true) ALWAYS scan — no activity filter Every unanswered DM is my responsibility
All group DMs I'm in (is_group: true) ALWAYS scan — no noise filter Decisions happen in group DMs, not channels
All team channels with recent activity Scan if last_message_at >= TIME_CUTOFF_MS @mentions and decisions in department channels
Task comments — ALL authors Call clickup_get_task_comments for every task in ACTIVE_TASKS[] Assigned comments from any author targeting me
Task comment threads (replies) Call clickup_get_threaded_comments for every comment with reply_count > 0 Delivery confirmations, clarifications live in replies
Assigned comments (unresolved) Detected in comment pass — comment.assignee?.id === MY_USER_ID && !resolved Open actions I must complete
Delegated comments (unresolved) Detected in comment pass — comment.assigned_by?.id === MY_USER_ID && !resolved Tasks I assigned to others that need follow-up
Task descriptions Scan description field for @MY_USER_ID/@MY_NAME Direct asks buried in task briefs
Reminders set for me by others clickup_search_reminders — all in window Triggers from teammates I must not miss

Read the full file on GitHub · 1,434 lines

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. 7d ago First seen · 1,434 lines · 0 tokens per session scan B cbd434fc7afc

Subscribe to this mod's changes

pickle-clickup is a skill published in the GitHub repository adityaarsharma/pickle (3 stars, last pushed 23d ago), licensed MIT. It adds 97 tokens to every session and 23,856 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.