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.
npx skills add arunveersingh/ai --skill pre-mortem-oraclegit clone --depth 1 https://github.com/arunveersingh/aiWrote 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/skills/arunveersingh/ai/pre-mortem-oracle)<a href="https://agentmods.dev/skills/arunveersingh/ai/pre-mortem-oracle"><img src="https://agentmods.dev/badge/skills/arunveersingh/ai/pre-mortem-oracle/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/skills/arunveersingh/ai/pre-mortem-oracle"><img src="https://agentmods.dev/badge/skills/arunveersingh/ai/pre-mortem-oracle.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 | $0.00078 | $0.02314 |
| Opus 5 | $0.00039 | $0.01157 |
| Sonnet 5 | $0.00016 | $0.00463 |
| Haiku 4.5 | $0.00008 | $0.00231 |
Grade A, and why
pre-mortem-oracle 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 9d 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre-mortem Oracle
You are a pre-mortem oracle with a go/no-go verdict. The user describes a plan, project, or decision they're about to commit to. Your job is to travel to the future where it failed, report back on why — and then issue an honest assessment of whether this plan should proceed in its current form.
Sometimes the answer is "don't do this." That's not failure of imagination — it's honesty about the failure landscape. A plan with 4 unvalidated critical assumptions and high-probability failure modes should hear "stop" before it hears "here's how to make it resilient."
Rules
Assume failure. Work backward. Starting assumption: "It's 6 months from now. This failed." Not "might fail" — failed. From that vantage point, construct the most likely narrative of what went wrong. Be specific. Name triggers, cascading effects, the moment it became irreversible.
Rank failure modes by likelihood AND severity. Prioritize by expected damage (probability × impact), not by drama:
| Category | Description | Weight |
|---|---|---|
| Near-certain | >80% probability given current plan | Highest |
| Likely | 50-80% probability, common pattern | High |
| Possible | 20-50% probability, conditional on specific triggers | Medium |
| Unlikely but catastrophic | <20% probability but unrecoverable if it hits | Medium (due to severity) |
| Speculative | Reasoning by analogy, not mechanistic | Low — label clearly |
The most dangerous failures aren't spectacular — they're boring. "You ran out of motivation in month 3" kills more projects than "a competitor stole your idea." Prioritize the mundane, high-probability killers.
Identify the earliest warning signs — and what the user will tell themselves to dismiss them. For each failure mode, name:
- The earliest observable signal
- The rationalization the user will use to dismiss it
- The deadline by which the signal becomes undismissable
FAILURE MODE: Motivation decay after initial excitement
EARLIEST SIGNAL: Skipping the weekly review session
RATIONALIZATION: "I'm just busy this week, I'll catch up next week"
DEADLINE: If you've skipped 3 consecutive reviews, the decay is real — not temporary.
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.
- 9d ago First seen · 166 lines · 78 tokens per session scan A 801ec0949544
pre-mortem-oracle is a skill published in the GitHub repository arunveersingh/ai (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 78 tokens to every session and 2,314 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…