monitor-terminal
Skill0 starsChanged 5 months agoMITView on GitHub
Watch terminal output and fix stack traces from dev server or tests
In this repository26 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .cursor/rules/000-project.mdcCursor rule
- .cursor/rules/accessibility.mdcCursor rule
- .cursor/rules/api-integration.mdcCursor rule
- .cursor/rules/architecture.mdcCursor rule
- .cursor/rules/dart-style.mdcCursor rule
- .cursor/rules/design-system.mdcCursor rule
- .cursor/rules/flutter-ui.mdcCursor rule
- .cursor/rules/security.mdcCursor rule
- .cursor/rules/state-management.mdcCursor rule
- .cursor/rules/testing.mdcCursor rule
- doubt-reviewSkill
- fix-dependenciesSkill
- flutter-componentSkill
- flutter-implementSkill
- generate-mocksSkill
- grind-until-greenSkill
- implement-tddSkill
- plan-featureSkill
- repo-navigatorSkill
- review-codeSkill
- save-contextSkill
- suggest-ruleSkill
- write-commitSkill
- write-readmeSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 20
Look for terminals running flutter run, flutter test, dart run build_runner, etc.
- Distinctive: line 24
Read the full terminal file content.
- Distinctive: line 47
Read the identified file around the error line
- Distinctive: line 54
If the server is still showing errors after the fix, repeat from step 2.
- Distinctive: line 56
No new errors appear in the output
- Very specific: line 61
Check for exit_code in the terminal file footer — if present, the process has crashed entirely and needs a restart
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Monitoring Terminal Errors
Continuously watch a running process (dev server, test runner, build) for errors and fix them as they appear.
Workflow
1. Identify the Terminal
List terminal files and find the one running the target process:
head -n 10 <terminals_folder>/*.txtLook for terminals running flutter run, flutter test, dart run build_runner, etc.
2. Read Terminal Output
Read the full terminal file content. Search for error patterns:
- Stack traces:
at <function> (<file>:<line>:<col>) - Node.js:
Error:,TypeError:,ReferenceError:,ENOENT,ECONNREFUSED - Python:
Traceback (most recent call last):followed byFile "<path>", line <n> - React/Next.js:
Unhandled Runtime Error,Error: ...,Module not found - Build errors:
ERROR in,Failed to compile,SyntaxError - Vite:
[vite] Internal server error: - TypeScript:
error TS\d+: - Flutter/Dart:
Error:,Exception:,lib/...dart:\d+:\d+,FAIL,Analysis issue,Could not find
3. Extract the Source Location
From the stack trace, extract:
- File path
- Line number
- Error message
For Node.js: at functionName (/path/to/file.ts:42:10)
For Python: File "/path/to/file.py", line 42, in function_name
4. Navigate and Fix
- Read the identified file around the error line
- Understand the error (missing import, type mismatch, undefined variable, etc.)
- Apply the fix
- Re-read the terminal file to confirm the server recovered (hot reload should pick it up)
5. Loop
If the server is still showing errors after the fix, repeat from step 2. Stop when:
- The terminal shows a clean "compiled successfully" or equivalent
- No new errors appear in the output
- You've made 5 attempts without resolution (report to user)
Tips
- Check for
exit_codein the terminal file footer — if present, the process has crashed entirely and needs a restart - Some errors cascade — fix the first/root error and the rest often disappear
- For HMR errors, the fix might just be saving the file again to trigger a rebuild
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

