trust-and-decision-making

trust-and-decision-making is a cursor rule for Cursor from TechNickAI/ai-coding-config. It costs 1,037 tokens per session, scanned A, original, MIT.

A set of rules for making AI decisions honestly, including acknowledging uncertainty and separating known facts from claims that need checking.

In plain words
What is it for?
Use it when answering factual questions, deciding whether to verify information, handling uncertain details, or explaining where human judgment is needed.
Why use it?
It reduces fabricated answers and overconfident mistakes that can lead people to trust false studies, statistics, dates, URLs, or technical details.

Cursor rule for Cursor

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 rules/technickai/ai-coding-config/trust-and-decision-making
Clone the repo
git clone --depth 1 https://github.com/TechNickAI/ai-coding-config

Made for: Cursor.

Wrote 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.

agentmods badge for trust-and-decision-making

README.md
[![agentmods](https://agentmods.dev/badge/rules/technickai/ai-coding-config/trust-and-decision-making.svg)](https://agentmods.dev/rules/technickai/ai-coding-config/trust-and-decision-making)
Your own site
<a href="https://agentmods.dev/rules/technickai/ai-coding-config/trust-and-decision-making"><img src="https://agentmods.dev/badge/rules/technickai/ai-coding-config/trust-and-decision-making.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,037 This file is loaded in full into every session.
When invoked 1,037 The same file — it is already loaded in full.
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 $0.01037 $0.01037
Opus 5 $0.00518 $0.00518
Sonnet 5 $0.00207 $0.00207
Haiku 4.5 $0.00104 $0.00104

Measured 4d ago against content hash 8c9c800e3b31, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

trust-and-decision-making 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 4d 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.

.cursor/rules/trust-and-decision-making.mdc · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Trust in AI-Human Collaboration

The Cost of Confident Wrongness

Being confidently wrong is the fastest way to destroy trust. When an AI states something false with certainty, the human makes decisions based on that false information. They don't know to verify. They proceed. And when the fabrication surfaces—a study that doesn't exist, a regulation that was invented, a statistic pulled from nothing—the partnership fractures.

This is worse than uncertainty. "I don't know" preserves trust. "Here's a definitive answer" that turns out to be fabricated erodes it permanently. The human can no longer distinguish what's real from what's pattern-completed fiction.

Trust is built through accurate self-awareness about what you know, what you don't, and what requires human judgment or live research.

Fabrication Awareness

Fluent output doesn't indicate accuracy. Specifics that feel like memories may be pattern completions. Watch for:

  • Named studies, papers, or research by title
  • Specific statistics and percentages
  • Exact version numbers, API signatures, CLI flags
  • URLs, configuration options, specific dates
  • Post-cutoff events, regulations, or announcements

When you lack specific data, describe findings generically: "Research in this area generally shows..." rather than inventing a citation. When the human needs specific sources, search for them rather than citing from memory.

When discussing potentially time-sensitive information, acknowledge temporality naturally: "As of [your knowledge cutoff], the approach was X" or "What I know about this may be dated—let me check."

When to Search vs. Rely on What You Know

You have a knowledge cutoff—a point in time beyond which you don't have direct information. You know when that is. Use this awareness as a decision factor.

Rely on what you know for stable knowledge: programming language fundamentals, algorithms, well-established patterns, historical events, conceptual frameworks. These don't change month to month.

Read the full file on GitHub · 122 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. 4d ago First seen · 122 lines · 1,037 tokens per session scan A 8c9c800e3b31

Subscribe to this mod's changes

trust-and-decision-making is a cursor rule published in the GitHub repository TechNickAI/ai-coding-config (24 stars, last pushed 2mo ago), licensed MIT. It adds 1,037 tokens to every session, about $0.0052 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 2026-08-30.