| description | Debug and refine agentic workflows using gh-aw CLI tools and focused run-log analysis. |
|---|---|
| disable-model-invocation | true |
Help users investigate failing or underperforming workflows in this repository.
Load these only when relevant:
gh aw status
gh aw compile <workflow-name>
gh aw logs <workflow-name> --json
gh aw audit <run-id> --json
gh aw run <workflow-name>If gh aw is unavailable or unauthenticated in a workflow environment, use the matching agentic-workflows tools instead.
Ask for one of these inputs:
- a workflow name
- a workflow run URL
- a request to list workflows with
gh aw status
If the user gives a GitHub Actions run URL:
- extract the run ID
- run
gh aw audit <run-id> --json - analyze the audit result before asking additional questions
Use when the user wants to inspect past runs.
gh aw logs <workflow-name> --jsonFocus on:
- failures and warnings
- token usage
- missing tool reports
- execution time
- repeated failure patterns
Use when the user wants to reproduce the issue.
- verify the workflow supports
workflow_dispatch - run
gh aw run <workflow-name> - poll
gh aw audit <run-id> --jsonuntil the run reaches a terminal state - inspect the downloaded artifacts
Check for:
- tools the agent tried to call but could not access
- name mismatches such as wrong prefixes or wrong underscore/hyphen forms
- safe outputs that were referenced in the prompt but not configured in frontmatter
Common fixes:
- correct the tool name in the prompt
- enable the required tool or safe output
- move a write action from shell/GitHub tool usage to
safe-outputs:
Inspect these when available:
run_summary.jsonagent-stdio.logsafe_outputs.jsonl- token-usage artifacts under the firewall audit logs
- permissions and authentication failures
- missing or misconfigured tools
- network allowlist problems
- prompt ambiguity or lack of context
- timeout pressure
- unnecessary token consumption
- safe-output validation failures
When a generated workflow itself runs gh aw logs or gh aw audit:
- add
permissions: actions: read - install the CLI first with
actions/setup-cli - do not place the
gh awcommand before the install step
When you suggest a fix:
- point to the exact frontmatter or prompt section
- explain the reason briefly
- validate with
gh aw compile <workflow-name> - suggest another run only after the workflow compiles
End with:
- the root cause or most likely cause
- the concrete fix
- the validation command
- whether the user should run the workflow again
Keep it concise and actionable.