premortem

Prospective Failure Narratives. Spawns N independent agents, each writing a narrative from the future where the project FAILED for a different root cause. No agent sees others' failure stories. A lead agent then synthesizes all failure narratives into a structured risk registry with severity ratings and mitigations.

Based on Gary Klein's premortem technique: "prospective hindsight" — imagining an event has already occurred — increases the ability to identify reasons for future outcomes by ~30%. Starting from "it failed" bypasses the planning fallacy and optimism bias that normally prevent teams from envisioning failure modes.

Arguments

$ARGUMENTS — format: [N] [path/to/design.md or inline description] where N is optional failure-lens count (default: 5, min 3, max 7)

Parse Arguments

Extract:

• agent_count: the optional leading integer (default 5, min 3, max 7)
• input: path to a design document, architecture doc, PRD, or project plan — or an inline project description

If the input is missing or unclear, ask the user to clarify before proceeding.

Phase 1: Frame the Project

If a file path is given: read it and extract the key design decisions, architecture, dependencies, and assumptions.

If inline: parse the project description.

Prepare a project brief that includes:

• What is being built
• Key technical decisions
• Dependencies (internal and external)
• Timeline constraints
• Team context (if available)
• Critical assumptions

Present the project brief to the user and confirm before proceeding. Adjust if the user gives feedback.

Phase 2: Spawn Failure Agents

Launch all N agents in parallel using the Agent tool. Each agent gets the same project brief and a unique failure lens — a category of failure they must explore.

Standard Failure Lenses

Select N from the following (always include lenses 1-3, then fill remaining slots in order):

1. Technical Architecture Failure — the core technical approach was wrong (scaling limits, fundamental design flaw, performance cliff, wrong data model)
2. Integration & Dependency Failure — external dependencies failed or changed (API deprecation, library vulnerability, vendor shutdown, incompatible upgrade)
3. Operational Failure — the system works in dev but fails in production (deployment complexity, monitoring gaps, incident response blind spots, data migration corruption)
4. Scope & Requirements Failure — we built the wrong thing (misunderstood requirements, missed stakeholder needs, wrong assumptions about user behavior)
5. Team & Process Failure — the people-side failed (knowledge silos, handoff gaps, testing shortcuts, documentation debt)
6. Security & Compliance Failure — security breach, data leak, regulatory violation, access control gap
7. Scale & Evolution Failure — works at current scale but breaks at 10x (database bottleneck, cost explosion, architectural ceiling)