Troubleshooting workflow
Harness Kit is a reusable Codex workflow layer for repositories that want a clean operating system around implementation work.
npx -y skills add HyunKN/harness-kit --skill troubleshooting-workflowAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Use when a concrete failure, regression, or confusing broken state must be debugged systematically and captured in `docs/troubleshooting`. Trigger for failing tests, broken builds, runtime errors, user-reported incidents, or environment-specific failures.
SKILL.md
1.2 KB, 204 tokens by cl100k_base, as published. Nobody here has run it
Troubleshooting Workflow
Treat failures as reusable incident history, not just something fixed in passing.
Default flow
- Stop adding unrelated work until the failure is understood.
- Preserve the symptom, reproduction steps, and affected paths.
- Narrow the fault before applying a fix.
- Record the actual root cause, not only the visible symptom.
- Validate the fix and note what proved it.
- Add a troubleshooting note in
docs/troubleshooting/when the incident would help another Codex user. - Decide whether the incident should also create a guardrail or decision record.
Good fit
- broken user-facing behavior
- failing tests or builds
- regressions after a recent change
- bugs that required more than one guess to understand
Avoid for
- already-understood failures with no reusable learning
- speculative cleanup not tied to a concrete incident
Resources
- See
references/incident-checklist.mdfor the core incident fields.
What ships with it: 2 files
418 B alongside SKILL.md
agents/
- openai.yaml141 B