unstick

unstick is a command for Claude Code from fatihkan/badi. It costs 0 tokens per session (917 once invoked), scanned A, original, MIT.

A guided troubleshooting command for when a coding task is blocked. It gathers the symptoms, attempted fixes, environment, and expected result before classifying the obstacle and suggesting next steps.

In plain words
What is it for?
Use it for errors such as failed API integrations, unclear requirements, debugging problems, and decisions between implementation options.
Why use it?
It replaces unstructured trial and error with a clear way to identify whether the problem is missing information, a technical fault, or a difficult choice.

Command for Claude Code

Written for Claude Code: installed under .claude/.

Part of the badi plugin — 81 skills, 86 commands, 30 agents, 7 hooks shipped together

Good fit Use it for errors such as failed API integrations, unclear requirements, debugging problems, and decisions between implementation options.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/fatihkan/badi/unstick
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.

Clone the repo
git clone --depth 1 https://github.com/fatihkan/badi

Made for: Claude Code.

Or install badi, the plugin that ships this one along with the rest of its 81 skills, 86 commands, 30 agents, 7 hooks.

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 unstick

README.md
[![agentmods](https://agentmods.dev/badge/commands/fatihkan/badi/unstick.svg)](https://agentmods.dev/commands/fatihkan/badi/unstick)
Your own site
<a href="https://agentmods.dev/commands/fatihkan/badi/unstick"><img src="https://agentmods.dev/badge/commands/fatihkan/badi/unstick.svg" alt="Measured on agentmods" height="20"></a>
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 917 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00000 $0.00917
Opus 5 $0.00000 $0.00458
Sonnet 5 $0.00000 $0.00183
Haiku 4.5 $0.00000 $0.00092

Measured yesterday against content hash f070ea0164c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

unstick 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.

.claude/commands/unstick.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Unblocking command. Finds a fast solution with a structured approach when you're stuck.

Required Tools

  • Read (code and context reading)
  • Grep (error and pattern search)
  • Glob (file discovery)
  • Bash (running tests, debugging)

Starting Format

From the user: "I'm stuck on [X] because of [Y]" Example: "I'm stuck on the API integration because of a CORS error"

Procedure (5 Steps)

Step 1: Capture the Blocker

Collect from the user:

  • What: Which task/operation is stuck? (X)
  • Why: What is the nature/cause of the blocker? (Y)
  • Tried: What has been attempted so far?
  • Error Message: The actual error output, if any
  • Expected: What did they expect to happen?
  • Actual: What happened instead?
  • Environment: Which environment? (local, staging, production)

Step 2: Classify

Assign the blocker to one of 5 categories:

A) Missing Information

  • Missing data, documentation, or API knowledge
  • Fix: Find and review the relevant sources
  • Tools: Grep, Read, documentation scan

B) Decision Paralysis

  • Stuck between multiple options
  • Fix: Comparative analysis of the options; list pros/cons
  • Approach: Start with "is it reversible?"; if reversible, pick the simplest

C) Circular Debugging

  • Hitting the same error repeatedly
  • Fix: Question the assumptions, narrow the problem area
  • Approach: Binary search — systematically narrow where the problem lives

D) Scope Confusion

  • Unclear what to do, vague requirements
  • Fix: Clarify requirements, define the smallest useful piece
  • Approach: the question "what is the smallest thing that could work?"

E) Environment Issues

  • Configuration, dependencies, access, version mismatch
  • Fix: Environment check, dependency verification
  • Approach: Reproduce in a clean environment, isolation test

Step 3: Activate the Analyst

Start the analysis per the classification:

Information gathering:

  • Read the relevant code and understand its context
  • Research the error message
  • Search for solutions to similar problems
  • Check the documentation

Read the full file on GitHub · 121 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. yesterday First seen · 121 lines · 0 tokens per session scan A f070ea0164c1

Subscribe to this mod's changes

unstick is a command published in the GitHub repository fatihkan/badi (7 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 917 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 2026-09-06.