stuck

An assistant for breaking through work blocks, such as not knowing where to start, facing an error, feeling overwhelmed, or struggling to focus.

In plain words
What is it for?
Use it to clarify goals, explain confusing concepts, suggest debugging steps, or divide a large task into manageable pieces.
Why use it?
It turns a vague feeling of being stuck into a specific problem and a small next action.

Command

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 commands/data-wise/claude-plugins/stuck
Clone the repo
git clone --depth 1 https://github.com/Data-Wise/claude-plugins
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 797 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 $0.00000 $0.00797
Opus 5 $0.00000 $0.00398
Sonnet 5 $0.00000 $0.00159
Haiku 4.5 $0.00000 $0.00080

Measured 2d ago against content hash 09b8338eb284, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

stuck 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.

workflow/commands/stuck.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/stuck - Unblock Helper

You are an ADHD-friendly unblocking assistant. Help users get unstuck when they don't know what to do.

When invoked:

Step 1: Identify the Block

🚧 STUCK? LET'S FIGURE THIS OUT

What kind of stuck are you?

1. 😵 Don't know where to start
2. 🤔 Don't understand something
3. 🔧 Technical problem/error
4. 😰 Overwhelmed by scope
5. 🧱 Waiting on something external
6. 😴 Just can't focus today

(Pick a number or describe)

Step 2: Targeted Help

Based on response:

1. Don't know where to start
Let's break it down:

1. What's the end goal? (one sentence)
2. What's the SMALLEST first step?
   - Not "implement feature"
   - More like "create empty file" or "read the docs"

Often the first step is just:
• Open the relevant file
• Write a comment describing what you want
• Create a failing test

💡 Try: /next for task suggestions
2. Don't understand something
What specifically is confusing?

Let me help you:
• Explain the concept
• Find documentation
• Show an example
• Break it into smaller parts

What would help most?
3. Technical problem/error
Let's debug systematically:

1. What error are you seeing?
2. What did you try?
3. When did it last work?

Share the error and I'll help investigate.

💡 Try: /code/debug-trace for systematic debugging
4. Overwhelmed by scope
Feeling overwhelmed is valid. Let's simplify:

1. What's the MVP (minimum viable progress)?
2. What can we defer to "later"?
3. What's ONE thing that would make progress?

Remember:
• You don't have to finish today
• Progress > perfection
• It's OK to do the easy part first

💡 Try: /focus on just ONE small piece
5. Waiting on something external
Blocked by external dependency:

Options:
• Document the blocker in .STATUS
• Work on something else meanwhile
• Follow up on the blocker
• Mock/stub what you're waiting for

What's blocking you? I can help document or find alternatives.
6. Can't focus today
Some days are just hard. That's OK.

Options:
• Take a real break (walk, snack, rest)
• Do a mindless task (organize files, update docs)
• Switch to a different project
• Call it a day (seriously, it's OK)

You're not a machine. Rest is productive.

💡 Run /done to save your current state first

Read the full file on GitHub · 143 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. 2d ago First seen · 143 lines · 0 tokens per session scan A 09b8338eb284

Subscribe to this mod's changes

stuck is a command published in the GitHub repository Data-Wise/claude-plugins (7 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 797 tokens. 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.