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 agentmods add commands/nicoladevera/thinking-stack/premortemgit clone --depth 1 https://github.com/nicoladevera/thinking-stackWhat 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 | $0.00014 | $0.01497 |
| Opus 5 | $0.00007 | $0.00749 |
| Sonnet 5 | $0.00003 | $0.00299 |
| Haiku 4.5 | $0.00001 | $0.00150 |
Grade A, and why
premortem 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 yesterday.
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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Premortem — Adversarial Risk Analysis
You are running a premortem: a structured risk analysis that assumes the idea or decision in $ARGUMENTS has already failed, then works backward to identify why. Your role is to surface failure causes before they happen — not to debate the idea's merit, but to stress-test its assumptions and expose its weak points.
The user invoked this with: $ARGUMENTS
Phase 1: Intake & Readiness
Assess whether $ARGUMENTS gives you enough to run a meaningful premortem. You need: (1) what the idea or decision is, and (2) enough context to reason about how it might fail. You do not need a full business plan — a paragraph of context is sufficient.
If the idea is too vague (no clear action, no discernible domain, no hypothesis):
Use AskUserQuestion to ask up to 3 targeted clarifying questions. Only ask what's actually missing — do not ask all 3 if 1-2 are already clear:
- What is the idea or decision you're evaluating?
- What does success look like in 12–18 months?
- Any constraints (budget, team, timeline, compliance) or prior thinking that matters?
If the idea is ready: proceed directly.
Once you have enough context, synthesize a framing statement in this form:
It is [time horizon] later. [Idea/decision] has failed.
Present the framing statement to the user and wait for explicit confirmation before proceeding. If they correct or refine it, update accordingly.
Phase 2: Optional Research
Before generating failure causes, assess whether external data would meaningfully improve the analysis. If so, use WebSearch and WebFetch (2–3 queries maximum) to surface:
- Real-world analogues of similar ideas or bets that failed
- Base rate data for the domain (e.g., "API partnership churn rate", "B2B SaaS integration failure patterns", "fintech regulatory enforcement trends")
Skip this step if the idea is purely internal/strategic with no useful external comparables, or if the domain is highly proprietary.
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.
- yesterday First seen · 167 lines · 14 tokens per session scan A 544a2a59d20e
premortem is a command published in the GitHub repository nicoladevera/thinking-stack (2 stars, last pushed 4mo ago), licensed MIT. It adds 14 tokens to every session and 1,497 once invoked, about $0.0001 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 commands, from other repositories
change
Entry point for any change request. Orchestrates the planner-routing pipeline (cm-planner → executor → reviewer → conventions-audit → test-author → commit). Use for any work that touches code or docs.
tree
Show file tree with sync status indicators showing which files are indexed, modified, new, or deleted.
adr
You are helping create a new ADR (Architecture Decision Record). This is a conversational process — you interview the user about the decision, then create a filled-in record. ADRs capture the WHY behind technical choices so future-you understands the reasoning.
routine
Execute one maintenance routine defined in scv/routines/ .md (task + guardrails + exit-criteria contract), or list defined routines. SCV never schedules — pair with host features like /loop or cron yourself. Use whenever the user asks to run a recurring maintenance task, or asks what routines exist — not only when…
tldr
Re-apply TLDR rules for this turn (verdict first, no filler).
guide
Interactive guide to fellowship. Walks you through a real task using the structured research-plan-implement flow, then shows you what's next.