prepare

A planning framework that examines how a decision could fail, identifies ways to prevent those failures, and defines realistic best and worst outcomes.

In plain words
What is it for?
Use it before making a plan or decision to run a premortem, rank failure modes, set prevention measures, describe success and failure, and check preparedness.
Why use it?
It exposes overlooked risks before work begins and gives you fallback actions if the plan goes wrong.

Command

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 commands/neurofoo/agent-skills/prepare
Clone the repo
git clone --depth 1 https://github.com/neurofoo/agent-skills
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 795 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 $0.00000 $0.00795
Opus 5 $0.00000 $0.00398
Sonnet 5 $0.00000 $0.00159
Haiku 4.5 $0.00000 $0.00080

Measured 2d ago against content hash 9d34a6006619, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prepare 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.

wrap/commands/prepare.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prepare to Be Wrong

Counter overconfidence by planning for both success and failure. Set tripwires and fallbacks before you need them.

Instructions

Assume you might be wrong. Plan for how you'll detect problems and what you'll do. This isn't pessimism—it's preparedness.

Output Format

Decision/Plan: [What you've decided to do]


Premortem

Imagine this decision failed completely. What happened?

It's 6 months later. This was a disaster. Looking back, what went wrong?

Failure Mode Likelihood Severity Was It Predictable?
[what failed] High/Med/Low High/Med/Low [Yes/No]
[what failed] High/Med/Low High/Med/Low [Yes/No]
[what failed] High/Med/Low High/Med/Low [Yes/No]

Which failures can we prevent now?

Failure Prevention
[failure] [how to prevent it]
[failure] [how to prevent it]

Bookend the Future

Best realistic case:

If everything goes well, what does success look like? [Description]

Worst realistic case:

If things go badly, what does failure look like? [Description]

Are we prepared for the worst case? [Yes/No/Partially]

What would make the worst case more survivable?

  • [Mitigation 1]
  • [Mitigation 2]

Set Tripwires

Decide in advance what would cause you to reconsider

Tripwire Trigger Condition Action If Triggered
Date [specific date to review] [reassess decision]
Metric [if X drops below Y] [specific action]
Event [if specific thing happens] [specific action]
Resource [if we spend more than X] [stop and evaluate]

Tripwire reminder set? [Where/how will you be reminded?]


Safety Net

If we're wrong, what's our fallback?

If This Happens Our Response
[scenario 1] [fallback plan]
[scenario 2] [fallback plan]

Read the full file on GitHub · 121 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 · 121 lines · 0 tokens per session scan A 9d34a6006619

Subscribe to this mod's changes

prepare is a command published in the GitHub repository neurofoo/agent-skills (111 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 795 tokens. 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.