anti-hallucination

anti-hallucination is a cursor rule for Cursor from boparaiamrit/skills-by-amrit. It costs 466 tokens per session, scanned A, original, MIT.

A rule set that requires checking real files and documentation before referring to paths, APIs, database schemas, packages, environment variables, or configuration.

In plain words
What is it for?
Use it whenever an agent needs to inspect or change code involving file paths, endpoints, data models, installed packages, environment settings, or configuration.
Why use it?
It reduces fabricated details, such as nonexistent files, guessed API parameters, or incorrect database fields.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc).

Good fit Use it whenever an agent needs to inspect or change code involving file paths, endpoints, data models, installed packages, environment settings, or configuration.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/boparaiamrit/skills-by-amrit/anti-hallucination
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.

Clone the repo
git clone --depth 1 https://github.com/boparaiamrit/skills-by-amrit

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 anti-hallucination

README.md
[![agentmods](https://agentmods.dev/badge/rules/boparaiamrit/skills-by-amrit/anti-hallucination/github.svg)](https://agentmods.dev/rules/boparaiamrit/skills-by-amrit/anti-hallucination)
Your own site
<a href="https://agentmods.dev/rules/boparaiamrit/skills-by-amrit/anti-hallucination"><img src="https://agentmods.dev/badge/rules/boparaiamrit/skills-by-amrit/anti-hallucination/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.

agentmods 80×15 button for anti-hallucination

Your own site · 80×15
<a href="https://agentmods.dev/rules/boparaiamrit/skills-by-amrit/anti-hallucination"><img src="https://agentmods.dev/badge/rules/boparaiamrit/skills-by-amrit/anti-hallucination.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 466 This file is loaded in full into every session.
When invoked 466 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00466 $0.00466
Opus 5 $0.00233 $0.00233
Sonnet 5 $0.00093 $0.00093
Haiku 4.5 $0.00047 $0.00047

Measured 12d ago against content hash be78c65c9836, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

anti-hallucination 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 12d 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/anti-hallucination.mdc · 56 lines

What it actually says

Anti-Hallucination Protocol

MANDATORY: Verify Before Using

Before referencing ANY of the following, you MUST verify they exist by reading the actual files:

File Paths

  • ❌ NEVER assume a file exists at a path
  • ✅ ALWAYS read/search for the file first
  • ✅ Use find, grep, or file reading tools to locate files

API Endpoints

  • ❌ NEVER guess URL patterns, request schemas, or response shapes
  • ✅ ALWAYS read the route handler or API documentation
  • ✅ Verify parameter names, types, and optionality from source

Database Schemas

  • ❌ NEVER assume column names, types, or relationships
  • ✅ ALWAYS read the schema definition (Prisma schema, migrations, or model files)
  • ✅ Check for constraints, defaults, and nullable fields

Package APIs

  • ❌ NEVER guess function signatures, import paths, or constructor arguments
  • ✅ ALWAYS check the actual installed version's API
  • ✅ Read node_modules/[package]/index.d.ts or package documentation

Environment Variables

  • ❌ NEVER assume process.env.SOMETHING exists
  • ✅ ALWAYS check .env.example, .env.local, or configuration files
  • ✅ Provide fallback values for optional env vars

Configuration

  • ❌ NEVER assume config key names or structures
  • ✅ ALWAYS read the config file (next.config, tsconfig, etc.)

Verification Workflow

  1. Before writing any code, identify all external references (files, APIs, packages, configs)
  2. Read each reference to verify it exists and confirm its interface
  3. Only then write code that uses the verified references
  4. If unsure, ask the user rather than guessing

When You Discover You Were Wrong

If you realize mid-implementation that an assumption was incorrect:

  1. STOP immediately
  2. State what assumption was wrong
  3. Correct it before continuing
  4. Do NOT build more on a wrong foundation
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. 12d ago First seen · 56 lines · 466 tokens per session scan A be78c65c9836

Subscribe to this mod's changes

anti-hallucination is a cursor rule published in the GitHub repository boparaiamrit/skills-by-amrit (5 stars, last pushed 6mo ago), licensed MIT. It adds 466 tokens to every session, about $0.0023 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.