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.
git clone --depth 1 https://github.com/sliamh11/DeusWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/sliamh11/deus/decision-pre-mortem)<a href="https://agentmods.dev/agents/sliamh11/deus/decision-pre-mortem"><img src="https://agentmods.dev/badge/agents/sliamh11/deus/decision-pre-mortem/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/sliamh11/deus/decision-pre-mortem"><img src="https://agentmods.dev/badge/agents/sliamh11/deus/decision-pre-mortem.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00045 | $0.00808 |
| Opus 5.5 | $0.00018 | $0.00323 |
| Sonnet 5.5 | $0.00009 | $0.00162 |
| Haiku 4.5 | $0.00005 | $0.00081 |
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 1mo 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.
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
-
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.
-
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.
-
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.
-
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.
-
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.
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.
- 1mo ago First seen · 57 lines · 45 tokens per session scan A 2b72e8b7b193
decision-pre-mortem is an agent published in the GitHub repository sliamh11/Deus (52 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 808 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other agents, from other repositories
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…
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.
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.
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.
ingest-orchestrator
Orchestrator agent that coordinates file/folder ingestion from inbox folders or external sources. Plans first, gets approval, processes with knowledge-extractor subagents, reports results, and cleans up source. Replaces ingest-coordinator per DIP-0021.
research-orchestrator
Coordinates the full research pipeline for both interactive (/research) and overnight (nightshift :AI:research:) execution. Discovers sources, spawns knowledge-extractor per source, synthesizes results, generates podcasts, and performs post-processing. Replaces daily-research-processor, research-post-processor, and…