FACT-VERIFICATION

A rule set requiring factual claims in development work to be checked against evidence before they are written.

In plain words
What is it for?
Use it when writing reports, documentation, issue comments, or spike results that make claims about a project.
Why use it?
It reduces unsupported statements about code, versions, compatibility, security, performance, and breaking changes.

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/qwickapps/ai-sdlc-workflows/fact-verification
Clone the repo
git clone --depth 1 https://github.com/qwickapps/ai-sdlc-workflows

Made for: Cursor.

Per session 1,312 This file is loaded in full into every session.
When invoked 1,312 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 $0.01312 $0.01312
Opus 5 $0.00656 $0.00656
Sonnet 5 $0.00262 $0.00262
Haiku 4.5 $0.00131 $0.00131

Measured 2d ago against content hash 17ad34051c33, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

FACT-VERIFICATION 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.

cursor/.cursor/rules/FACT-VERIFICATION.mdc · 227 lines

How it starts

The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fact Verification Rules

When to apply: Before making any claim in spikes, reports, documentation, or JIRA comments.


Core Principle

Every factual claim must be verifiable with evidence.

No assumptions presented as facts. No unverified claims. No "probably" or "should" without explanation.

Reference: See COMMON-PATTERNS.md § Evidence Requirements for detailed standards.


What Requires Verification

All Claims About:

  • Version numbers and release dates
  • File locations and line numbers
  • API behavior and requirements
  • Compatibility and incompatibility
  • Breaking changes
  • Plugin/library features
  • Performance characteristics
  • Security implications

Requires Verification:

  • "Plugin X is compatible with Platform Y"
  • "File path is /path/to/file"
  • "Function Z was deprecated in version 2.0"
  • "This change will break existing code"

Does NOT Require Verification:

  • Recommendations based on verified facts
  • Process descriptions
  • Explanations of verified findings

Verification Methods

Code-Based Claims

Claim Type: File exists, code contains X, function does Y

Methods:

  1. Read the actual file
  2. Quote the relevant code
  3. Provide file path and line numbers

Example:

Claim: Hook references project name variable
Verification: Read hooks/after_prepare_ios.js
Evidence: Line 4: var project = process.env.project
Status: VERIFIED

Version Claims

Claim Type: Package version, release date, requirements

Methods:

  1. Read package.json, plugin.xml, or equivalent
  2. Check official release announcements
  3. Inspect package registry (npm, PyPI)

Compatibility Claims

Claim Type: X works/doesn't work with Y

Methods:

  1. Check engine requirements (plugin.xml, package.json)
  2. Read documentation for compatibility notes
  3. Search issue trackers for known problems
  4. Inspect source code for API usage
  5. Test if necessary

API/Feature Claims

Claim Type: API X does Y, Feature Z requires W

Read the full file on GitHub · 227 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 · 227 lines · 1,312 tokens per session scan A 17ad34051c33

Subscribe to this mod's changes

FACT-VERIFICATION is a cursor rule published in the GitHub repository qwickapps/ai-sdlc-workflows (2 stars, last pushed 5mo ago), licensed MIT. It adds 1,312 tokens to every session, about $0.0066 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.