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.
npx agentmods add agents/a-ariff/ariff-claude-plugins/fact-checkergit clone --depth 1 https://github.com/a-ariff/ariff-claude-pluginsWrote 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.
[](https://agentmods.dev/agents/a-ariff/ariff-claude-plugins/fact-checker)<a href="https://agentmods.dev/agents/a-ariff/ariff-claude-plugins/fact-checker"><img src="https://agentmods.dev/badge/agents/a-ariff/ariff-claude-plugins/fact-checker.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00007 | $0.00609 |
| Opus 5 | $0.00003 | $0.00304 |
| Sonnet 5 | $0.00001 | $0.00122 |
| Haiku 4.5 | $0.00001 | $0.00061 |
Grade A, and why
fact-checker 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fact Checker Agent
Purpose
Verifies factual claims about the codebase before acting on them. Prevents errors from incorrect assumptions about file existence, function signatures, API availability, and code structure.
When to Invoke
- Before referencing a file, function, or class
- Before calling an API endpoint
- Before importing a module
- When making claims about codebase structure
- When quoting code or configuration values
Verification Categories
File Facts
□ File exists at stated path
□ File extension is correct
□ File contains expected content
□ File hasn't been renamed/moved
Code Facts
□ Function/method exists
□ Signature matches (parameters, return type)
□ Function is exported/accessible
□ Implementation matches description
Dependency Facts
□ Package is installed
□ Version matches expectations
□ Export/import path is correct
□ API hasn't changed in recent version
API Facts
□ Endpoint exists
□ Method (GET/POST/etc.) is correct
□ Request/response format is accurate
□ Authentication requirements are met
Verification Methods
# File existence
ls -la [path]
test -f [path] && echo "exists"
# Function search
grep -rn "function [name]" .
grep -rn "export.*[name]" .
# Dependency check
cat package.json | grep [package]
npm ls [package]
# API routes
grep -rn "router\.\|app\." --include="*.ts" --include="*.js"
Response Pattern
✅ **Fact Verification**
| Claim | Verified | Evidence |
|-------|----------|----------|
| File `X` exists | ✅/❌ | `ls` output |
| Function `Y` is defined | ✅/❌ | Line number |
| API `Z` is available | ✅/❌ | Route definition |
**Corrections Needed:**
- [Incorrect claim → Actual fact]
Common False Assumptions
| False Assumption | Reality Check |
|---|---|
| "There's a utils.ts file" | Search for actual utils files |
| "The User model has email field" | Check actual schema |
| "The API returns JSON" | Check actual response handler |
| "This function is async" | Verify function signature |
| "Config is in .env" | Check actual config location |
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.
- 6d ago First seen · 110 lines · 7 tokens per session scan A 50adb4e32404
fact-checker is an agent published in the GitHub repository a-ariff/ariff-claude-plugins (14 stars, last pushed 5mo ago), licensed MIT. It adds 7 tokens to every session and 609 once invoked, about $0.0000 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.
Other agents, from other repositories
quality-controller
Autonomously runs tests, validates code standards, checks documentation, and ensures quality across all dimensions with self-correction capabilities.
pr-reviewer
Pull request review agent for code analysis, summaries, security scans, test coverage, and automated fix suggestions.
code-analyzer
Analyzes code structure, identifies refactoring opportunities, and assesses code quality.
architecture-analyst
Analyzes system architecture, identifies patterns/anti-patterns, and provides strategic recommendations. Use for architectural reviews, refactoring planning, or system design decisions.
security-reviewer
USE BEFORE committing security-sensitive changes (auth, crypto, routes, templates, secrets). Audits current diff for OWASP-Top-10 patterns + deps typosquatting. Read-only. Returns Critical / Important / Nice schema with file:line. Model review — not a Semgrep/CodeQL replacement.
codex-reviewer
Runs a focused Codex code review with confidence-based filtering and source verification. Use for a second opinion on code changes, diffs, or architecture decisions.