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.
git clone --depth 1 https://github.com/fatihkan/badiWrote 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/commands/fatihkan/badi/unstick)<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>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 | $0.00000 | $0.00917 |
| Opus 5 | $0.00000 | $0.00458 |
| Sonnet 5 | $0.00000 | $0.00183 |
| Haiku 4.5 | $0.00000 | $0.00092 |
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.
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
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 · 121 lines · 0 tokens per session scan A f070ea0164c1
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.
Other commands, from other repositories
check-cache-bugs
Audit Claude Code setup for cache bugs (CC#40524) — sentinel, --resume/--continue, attribution header + ArkNill B3/B4/B5.
investigate
Systematic root-cause debugging — find the cause before writing any fix.
optimize
Analyze and suggest performance improvements for code, queries, or systems.
diagnose
Interactive troubleshooting assistant for Claude Code issues.
audit-agents-skills
Audit quality of agents, skills, and commands in a Claude Code project.
land-and-deploy
Merge PR, wait for CI, verify deploy, run canary — the complete landing pipeline.