Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Pre Mortem

    2

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

    Free

    16 uses5.0 (1 review)
    pre-mortem

    pre-mortem

    Example session with this skill installed

    Run a pre-mortem on our B2B SaaS launch for Q3. We need to identify specific failure modes and move past surface-level risks to find the underlying behavioral attractors.

    • Read your context and instructions
    • Compiled the pre-mortem

    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.

    Connects securely to your tools. The creator never sees your data.

    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: <exact text>" 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.

    • Requires user-supplied project context; cannot run autonomously without a project to analyze.
    • Behavioral attractor test (Phase 3) requires the model to actually re-derive failure modes after the FORBIDDEN line is written. Weaker models may pattern-match around the suppression anchor instead of running a fresh derivation; results degrade accordingly.
    • Pre-commitment enforcement layer (Phase 5) requires real humans to fill the NAMED OWNER and EXTERNAL WITNESS roles. Solo founders can use the skill but the external-witness field becomes harder to populate honestly; the renegotiation clause partially compensates.
    • Not a substitute for domain-specific risk analysis (security threat modeling, financial risk assessment, regulatory compliance review). The skill catches behavioral and execution failure modes, not domain-technical ones.
    • Ordinal probability ranking deliberately avoids point estimates. Teams that need calibrated forecasts for resource allocation should pair this skill with a separate forecasting workflow.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    5.0
    1 review
    5
    1
    4
    0
    3
    0
    2
    0
    1
    0

    This skill has been used 16 times.

    Trust & safety

    Security scan

    Security scan passed 6 months ago

    • Free with an Agensi account

    Permissions

    No special permissions declared or detected

    Listed6 months ago

    What's inside

    Frequently Asked Questions

    Unlike standard risk lists, this skill uses a five-phase procedure including 'behavioral attractor tests' and 'pre-commitment enforcement' to ensure identified risks result in binding, accountable project changes rather than just a static document.

    The file contains a structured framework, ordinal probability ranking systems, pre-commitment enforcement layers, a worked example for B2B SaaS, and anti-pattern checklists to keep the analysis on track.

    This skill is designed for any LLM-augmented planning tool or agentic framework that supports multi-step procedures, specifically those where you can maintain state across phased execution.

    The skill includes a 'meta-reflection' self-check and an 'output discipline' gate that requires the agent to complete specific validation steps (like naming owners and external witnesses) before the process can advance.

    Yes, it is specifically built for founders, PMs, and tech leads who need high-stakes project reviews where the cost of failure is significant, such as architecture changes or major product launches.

    No complex setup is required; the skill is a self-contained procedure that can be imported into your agent's context window or system prompt to immediately begin a guided pre-mortem session.

    New in Business & Operations

    Free