2
    pre-mortem

    pre-mortem

    by Frank Brsrk

    Run disciplined pre-mortems that replace generic risk lists with project-specific failure modes and binding decisions.

    Updated May 2026
    0 installs

    Free

    One-time purchase

    ⚡ Also available via Agensi MCP — your AI agent can load this skill on demand via MCP. Learn more →

    Included in download

    • Downloadable skill package
    • Works with Codex CLI, Cursor
    • Instant install

    See it in action

    INPUT: a B2B SaaS team running a pre-mortem on their Q3 launch.

Phase 2 (free generation) surfaces 8 failure modes. Top by team consensus: "We ship without enterprise SSO and lose three pipeline deals to competitors." 

Phase 3 (behavioral attractor test) writes:

  FORBIDDEN FROM RE-DERIVATION: "We ship without enterprise SSO and lose three pipeline deals to competitors."

The team re-derives from scratch and produces: "We ship without SOC2 and the same three deals stall in security review." Same structural failure (compliance gap blocks enterprise close), different surface. Behavioral attractor confirmed: the team's recurring failure mode is "we under-invest in enterprise procurement requirements." This is now a higher-priority finding than any single technical gap.

Phase 4 (probability/impact) ranks: HIGH probability × Severe impact, anchored against B2B SaaS reference class (founder-led companies historically under-invest in compliance until forced).

Phase 5 (pre-commitment design) produces three devices. Each ships with three fields:

  Device: "SSO + SOC2 readiness assessment by 2026-07-15."
  NAMED OWNER: CTO (personally answers if the device is breached)
  EXTERNAL WITNESS: lead investor at next board meeting (told the commitment date)
  RENEGOTIATION CLAUSE: can be deferred only if a paying enterprise customer signs without SSO/SOC2 as a contractual requirement.

OUTPUT DISCIPLINE Step 0 then fires the META-REFLECTION self-check before the analysis ships: did the FORBIDDEN line genuinely re-derive (yes), did ordinal probability anchor to a reference class (yes), do all enforcement devices have three fields (yes), is the analysis traceable to the launch goal (yes), did the team avoid planning-fallacy laundering (yes). Ship.

    Screenshots

    About This Skill

    The Klein 1989 pre-mortem method asks teams to imagine the project has failed and reason backward to causes. It works, sometimes. The version most teams run is decorative: failure modes get named in a meeting, written into a doc, and then ignored when the project ships. This skill ships a pre-mortem with the forcing functions that make the method bind on actual behavior. What's in the file: - Five-phase procedure (premortem framing, free generation of failure modes, behavioral attractor test, probability/impact assessment, pre-commitment design) with explicit steps each phase must complete before advancing. - Behavioral attractor test (Phase 3): after generating failure modes, remove the highest-probability one and re-derive. If the same structural failure re-emerges with different surface details, the team has a behavioral attractor not a discrete risk. The skill writes a literal "FORBIDDEN FROM RE-DERIVATION: " line into context as an in-context suppression anchor for the LLM running the analysis. - Ordinal probability ranking (Phase 4): HIGH/MEDIUM/LOW × Existential/Severe/Recoverable/Minor, anchored against named reference classes. No fake-precision point estimates. - Pre-commitment enforcement layer (Phase 5): every pre-commitment device requires three fields explicitly written down. NAMED OWNER (the person who personally answers if the device is breached), EXTERNAL WITNESS (someone outside the team who is told what the commitment is), and RENEGOTIATION CLAUSE (the conditions under which the commitment can be dropped without it being a quiet failure). Without these three fields, the device is decorative. - Worked example demonstrating all four mechanics on a realistic B2B SaaS launch scenario. - META-REFLECTION self-check inlined into OUTPUT DISCIPLINE step 0 as a hard gate. - Anti-patterns section catching common pre-mortem failures (planning-fallacy laundering, narrative compliance in Phase 3, pre-commitments without enforcement). Built for: founders running pre-launch reviews, project managers running risk sessions, tech leads running architecture decisions where the cost of being wrong is high, and LLM-augmented planning tools that need a procedure that fires per-step rather than once at the top. Cites: Klein 2007 HBR, Kahneman planning fallacy, Tetlock calibration, Hubbard probability estimation, Annie Duke pre-commitment.

    Use Cases

    • Stress-test a product launch by imagining a 90% churn scenario backward.
    • Surface organizational and regulatory blind spots before a major pivot.
    • Create binding 'Ulysses Contracts' for high-stakes strategic decisions.
    • Conduct planning audits for internal migrations and infrastructure changes.

    Reviews

    No reviews yet - be the first to share your experience.

    Only users who have downloaded or purchased this skill can leave a review.

    Security Scanned

    Passed automated security review

    Permissions

    No special permissions declared or detected

    Tags

    risk-assessment
    project-management
    strategy
    decision-making
    planning

    Pure SKILL.md content; no runtime dependencies, no framework version requirement. Works with any compatible agent (Claude Code, Codex CLI, Cursor, Copilot, Gemini CLI). Best with reasoning-capable models, because the behavioral attractor test in Phase 3 requires genuine re-derivation rather than pattern-matching around the FORBIDDEN line.

    Creator

    Frank Brsrk

    Building Ejentum, a cognitive harness API for AI agents. Small structured pieces of context retrieved at inference time, so the agent reasons through a task instead of pattern-matching to a generic answer. Adversarial systems thinking is the other thing I'm into: chaos engineering, pre-mortems, blast-radius design. Those skills sit alongside the Ejentum harness wrappers on this profile. Solo builder, open source most of what I make.

    Frequently Asked Questions

    Learn More About AI Agent Skills

    Similar Skills

    code-reviewer

    Reviews your code for bugs, security vulnerabilities, logic errors, performance issues, and style violations. Organizes findings by severity and suggests fixes with code examples.

    Free254 installs

    git-commit-writer

    Writes conventional commit messages by analyzing your staged git changes. Detects commit type, scope, and breaking changes automatically.

    Free113 installs

    readme-generator

    Generates a complete, polished README.md by scanning your actual project structure, dependencies, and code.

    Free75 installs

    env-doctor

    Diagnoses why your project will not start. Checks runtime versions, dependencies, environment variables, databases, ports, and build artifacts systematically.

    Free58 installs

    Free