wrap

A four-part decision process for broadening choices, testing assumptions against reality, considering consequences, and choosing what to do.

In plain words
What is it for?
Use it for product, engineering, or personal decisions where you need to compare alternatives, examine assumptions, and plan how to act on the choice.
Why use it?
It reduces common decision mistakes such as considering only one option or looking mainly for evidence that supports a preferred answer.

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/wrap
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 917 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 $0.00917
Opus 5 $0.00000 $0.00458
Sonnet 5 $0.00000 $0.00183
Haiku 4.5 $0.00000 $0.00092

Measured 2d ago against content hash 7f54f2b93583, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

wrap 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/wrap.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

WRAP Decision Framework

Apply the complete WRAP framework to make a better decision by countering the four villains of decision-making.

Instructions

Work through all four phases sequentially. Each phase targets a specific cognitive bias that undermines good decisions.

Output Format

Decision: [What are we deciding?] Context: [Key constraints and stakes]


W: WIDEN Your Options

Counter: Narrow Framing ("Should I do X?" → "What are all my options?")

Current Framing How is the decision currently framed? (Often as "whether or not")

Expanded Options

# Option Why It's Worth Considering
1 [option] [rationale]
2 [option] [rationale]
3 [option] [rationale]
4 [option] [rationale]

Option-Finding Techniques Used

  • Vanishing options test: "If you couldn't do X, what would you do?"
  • Opportunity cost: "What else could you do with this time/money?"
  • Find someone who solved it: "Who's had this problem?"
  • Multi-track: "What if we tried A and B simultaneously?"

R: REALITY-TEST Your Assumptions

Counter: Confirmation Bias (seeking evidence that confirms what we want)

Key Assumptions

Assumption How Would We Know If Wrong?
[assumption 1] [test]
[assumption 2] [test]
[assumption 3] [test]

Consider the Opposite For each option, what would it take to be convinced it's wrong?

Base Rates What usually happens in situations like this? What's the base rate of success?

Ooch Is there a small experiment we can run to test this before fully committing?

Option Small Test What We'd Learn
[option] [test] [insight]

A: ATTAIN Distance Before Deciding

Counter: Short-term Emotion (deciding when angry, excited, or desperate)

10/10/10

Time Horizon How will you feel about this decision?
10 minutes [how you feel now]
10 months [how you'll likely feel]
10 years [long-term perspective]

Read the full file on GitHub · 138 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 · 138 lines · 0 tokens per session scan A 7f54f2b93583

Subscribe to this mod's changes

wrap 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 917 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.