
Terminal Tools Troubleshooting
Diagnoses surprising results from terminal-tools calls, such as empty output, null exit codes, and expired handles.
- Repository
- aden-hive/hive
- Stars
- 11,132
- Licence
- Apache-2.0
- Files
- 1 file
What it does
This is a reference guide that an AI agent loads only when a terminal command tool returns something unexpected. It matches the symptom (for example empty output, exit_code null, an expired output handle, or a 'too many jobs' error) to a short list of likely causes and fixes. It tells the agent how to read the semantic status fields and when a warning is informational rather than a failure.
Great for
- Developers building or debugging agents that run shell commands through the terminal-tools interface
- Anyone troubleshooting why a background job, PTY session, or output capture behaved unexpectedly
Skip it if
- General coding or shell help outside the terminal-tools interface, since the recipes only cover that tool's behaviour
- Environments that need the agent to run commands unattended without review, because the file itself notes that warnings are a prompt to verify side effects
Try asking
- “My terminal_job call returned empty stdout with no error. What could be causing it?”
- “Why is exit_code null on this command?”
- “My output_handle says expired. How do I avoid that next time?”
- “I get 'too many jobs' when starting commands. How do I free up slots?”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 1 original files, the Apache-2.0 licence and an attribution note.
terminal-tools-troubleshooting.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip terminal-tools-troubleshooting.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip terminal-tools-troubleshooting.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 3
Ask for the task
No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.
Get better results
- Load this skill only when a specific symptom appears, as its description advises, rather than preloading it.
- Check semantic_status and semantic_message before treating a non-zero exit code as a failure.
- Review any warning flags before continuing, since they often signal a destructive command like rm -rf or git push --force.
What's inside
- SKILL.md
Redistributed unmodified from aden-hive/hive under the Apache-2.0 licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.