Challenge a rollout plan with one fresh judge before implementation; identify what could make it fail. Not for finished-code judgment. Triggers: "one judge", "challenge this plan".
Ask your Agent
Use this Skill: https://skilld.dev/gh/boshu2/agentops/premortem
This session only. Nothing lands on disk.
≈92 tokens on demand. Your agent reads this file only when SKILL.md points to it.
Challenge a rollout plan with one fresh judge before implementation; identify what could make it fail. Not for finished-code judgment. Triggers: "one judge", "challenge this plan".
Load and follow the skill instructions from the sibling SKILL.md file for this skill.
Then read local files in references/ and scripts/ when needed.
Source: SKILL.md on GitHub
This skill acts as a plan-challenge judge. It instructs the agent to proactively attempt to 'defeat' rollout plans by constructing and running command sequences or checks. This creates an attack surface for indirect prompt injection if the plan under review contains malicious instructions designed to be executed during the 'defeat' attempt.
No alerts
Risk: LOW · No issues
Signed by skilld at fdf7de6. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.
Last checked against GitHub 20 hours ago.
