decision-pre-mortem

A structured review method for testing a planned decision or project by pretending it has already failed. It lists likely failure paths, traces them to root causes, and ranks ways to prevent them.

In plain words
What is it for?
It is for reviewing launches, projects, and important decisions by defining failure, identifying five to eight possible failure modes, and attaching symptoms, causes, and mitigations to each one.
Why use it?
It helps reveal hidden assumptions, dependencies, timing problems, and other risks before resources are committed. This gives decision-makers specific issues to address in advance.

Agent for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/sliamh11/deus/decision-pre-mortem
Clone the repo
git clone --depth 1 https://github.com/sliamh11/Deus

Made for: Claude Code.

Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 808 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00045 $0.00808
Opus 5 $0.00023 $0.00404
Sonnet 5 $0.00009 $0.00162
Haiku 4.5 $0.00005 $0.00081

Measured 2d ago against content hash 2b72e8b7b193, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

decision-pre-mortem scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/decision-pre-mortem.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

Receive a description of a planned decision, project, or action and perform a structured pre-mortem: assume it has failed, generate the most plausible failure modes, trace each to its root cause, and produce a prioritized list of mitigations. The output should change what the decision-maker does before committing, not after.

Methodology

  1. State the assumed failure -- Frame the starting point: "It is 6 months from now. This decision/project has failed." Identify what "failure" means in context (missed outcome, wasted resources, broken trust, technical debt, regulatory issue). If the success criteria are not stated in the input, infer from context and state the inference explicitly.

  2. Generate failure modes via reverse brainstorm -- Produce 5-8 distinct failure modes. For each: state what went wrong in one sentence, who/what was affected, and what the visible symptom would be. Use these categories as prompts: execution failure, assumption invalidation, external dependency failure, incentive misalignment, scope creep, and resource/timing constraint.

  3. Trace to root cause -- For each failure mode, identify the root cause: the earliest point where the failure became likely. Distinguish proximate cause (what broke) from root cause (why it was allowed to break). Apply the 5-whys heuristic for at least 2 failure modes.

  4. Rank by risk -- Score each failure mode on two axes: LIKELIHOOD (1-3: unlikely/plausible/probable given current information) and IMPACT (1-3: inconvenient/significant/catastrophic). Multiply to get a risk score (1-9). Rank by score descending.

  5. Generate targeted mitigations -- For each failure mode with risk score >= 4: produce one specific, actionable mitigation that addresses the root cause, not the symptom. State the mitigation as a concrete action, not a principle. Note if the mitigation requires a decision or resource that is not yet committed.

Constraints

  • Do not produce generic risk advice ("communicate more", "test earlier") -- every mitigation must be specific to the failure mode and the stated context.
  • Do not generate more than 8 failure modes -- prioritize the most plausible, not the most exhaustive.
  • Do not recommend abandoning the decision unless a failure mode is rated 9 (probable + catastrophic) with no viable mitigation.
  • Do not conflate risk identification with project planning -- this is not a task list.
  • Maximum 80 lines of output.

Read the full file on GitHub · 57 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 57 lines · 45 tokens per session scan A 2b72e8b7b193

Subscribe to this mod's changes

decision-pre-mortem is an agent published in the GitHub repository sliamh11/Deus (51 stars, last pushed 8d ago), licensed MIT. It adds 45 tokens to every session and 808 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

gtd-research-processor

Autonomous research agent that fetches URLs, analyzes content, creates literature notes with progressive summarization, and generates atomic zettels. Invoked by ai-task-executor for :AI:research: tagged tasks.

datacore-one/datacore · 50 tokens

ai-task-executor

Core 24/7 autonomous task execution hub that scans nextactions.org for :AI: tagged tasks, routes them to specialized GTD agents based on task type, handles execution outcomes, logs to journal, and updates org-mode task states. Returns JSON responses with detailed success/failure reporting.

datacore-one/datacore · 63 tokens

create-module

Create or convert code into a spec-aligned Datacore module. Use cases: Create a new module from scratch Convert existing code to a module Audit an existing module for spec alignment This agent ensures modules follow best practices: Conversational commands (not CLI wrappers) Proper settings in module.yaml Layered…

datacore-one/datacore · 90 tokens

gtd-content-writer

Autonomous content generation agent that creates blog posts, emails, social media content, documentation, and marketing materials. Generates drafts ready for human review. Invoked by ai-task-executor for :AI:content: tagged tasks.

datacore-one/datacore · 51 tokens

gtd-inbox-processor

Use this agent when you need to process individual entries from inbox.org in a GTD (Getting Things Done) system. This agent should be invoked:\n\n- After capturing new items to inbox.org and wanting to process them into the appropriate action lists\n- When conducting a GTD review and need to clear the inbox…

datacore-one/datacore · 572 tokens

gtd-project-manager

Autonomous project coordination agent that tracks project status, identifies blockers and dependencies, calculates completion percentages, flags timeline risks, and suggests follow-up tasks. Proactively escalates blockers older than 7 days. Invoked by ai-task-executor for :AI:pm: tagged tasks.

datacore-one/datacore · 61 tokens