All skills
simota avatar

/omen

@c805268
by shingo imotasimota/agent-skills85 stars
15

Enumerating failure modes via pre-mortem analysis. Systematically identifies failure scenarios for plans, designs, and features, scoring them with RPN/AP. Does not write code.

Requires /judge

Use this Skill: https://skilld.dev/gh/simota/agent-skills/omen

This session only. Nothing lands on disk.

referenceautorun-schema.md

≈484 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Omen — AUTORUN _STEP_COMPLETE Schema

Parse _AGENT_CONTEXT from the orchestrator to determine analysis scope, target system, and work mode. If _AGENT_CONTEXT specifies a LENS domain, restrict analysis to that domain.

_STEP_COMPLETE:
  Agent: Omen
  Status: SUCCESS | PARTIAL | BLOCKED | FAILED
  Output:
    deliverable: [pre-mortem report / FMEA table]
    parameters:
      work_mode: "[DEEP | RAPID | LENS]"
      failure_modes_count: "[count]"
      critical_rpn_count: "[RPN > 200 or AP=H count]"
      max_rpn: "[highest RPN]"
    tri_engine:                                  # present only when `multi` Recipe ran
      engines_run: [actual usable engines]  # authorized and actually invoked
      engines_failed: [list or none]
      pattern_type: "D"                          # Divergence-primary
      concurrence_distribution:
        UNIVERSAL: [count]
        LIKELY: [count]
        VERIFIED-DIVERGENT: [count]
      severity_9_clusters: [count]               # CRITICAL gate triggers
      composite_priority_top_N:                  # top N clusters by concurrence_weight × RPN
        - cluster_id: "FM-NNN"
          engine_concurrence: "[codex+agy+claude] | [codex+agy] | [codex-verified] | ..."
          composite_priority: "[number]"
          rpn_max: "[number]"
          rpn_variance: "[max-min across engines, calibration disagreement signal]"
          severity_critical: "[true if any S≥9 in cluster, else false]"
      divergent_spotlight:                       # VERIFIED-DIVERGENT modes that survived grounding
        - cluster_id: "FM-NNN"
          surfaced_by: "codex | agy | claude"
          blindspot_class: "[failure class the other engines structurally missed]"
      rejected: [count + top categories — hallucination / implausible / already-mitigated / out-of-scope]
  Next: [Ripple | Magi | Triage | Beacon | Radar | Sentinel | DONE]
  Reason: [Why this next step]

Source: SKILL.md on GitHub

1 alert13d4 checks · Risk HIGH
  • Gen Agent Trust Hub13d

    The Omen skill performs pre-mortem analysis but contains instructions to bypass security permissions when calling sub-agents via external CLI tools. It also presents a significant attack surface for indirect prompt injection by processing untrusted documentation and generating instructions for downstream agents without sanitization.

  • Socket13d

    No alerts

  • Snyk13d

    Risk: LOW · No issues

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at c805268. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 3 days ago.

Activeupdated 2 weeks ago

README badge

README badge for simota/agent-skills/omen