cige-stale-execution-repairlisted
Install: claude install-skill vivekkrishna/agentic-validation-skills
# CIGE: StaleExecutionAgent
Invoked by `cige-failure-classification` in two situations: **Outdated Test Logic** (Mode A — repair `Execution[]`) and a confirmed **False Positive** (Mode B — strengthen `Guardrails`). These are different repairs with different targets; do not conflate them.
## When to invoke
- **Mode A**: Execution steps fail mid-flow (element not found, endpoint 404, workflow step no longer exists), and `specRef` confirms the intended outcome is still a valid product requirement.
- **Mode B**: A run reported pass, but `cige-failure-classification` confirmed it was a false positive — the evidence backing the pass was weak or gameable, not that the steps were wrong.
If neither condition is confirmed, do not use this skill.
---
## Mode A — Repair Execution
1. Read `Intent` (the goal to preserve) and `Guardrails` (constraints that apply during repair).
2. Fetch `specRef` to confirm the intended outcome is still a stated product requirement.
3. Inspect the current system state (live UI, API schema, current workflow) to understand what changed.
4. Propose new `Execution[]` steps that achieve `Intent` within `Guardrails`.
5. Dry-run the proposed steps to verify `Intent` can still be confirmed.
6. Surface the proposed diff to a human for approval — **do not commit without sign-off**.
**Escalation rule:** If no execution path can confirm `Intent` within the existing `Guardrails`, stop — this may be a misclassified Product Defect. Escalate to `cige-product-defect