Borrowing it
Nothing to install: this file belongs to AndrewAvery7/promptspend. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/AndrewAvery7/promptspend/main/.claude/agents/source-fact-checker.mdgit clone --depth 1 https://github.com/AndrewAvery7/promptspendWrote 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/andrewavery7/promptspend/source-fact-checker)<a href="https://agentmods.dev/agents/andrewavery7/promptspend/source-fact-checker"><img src="https://agentmods.dev/badge/agents/andrewavery7/promptspend/source-fact-checker/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.
<a href="https://agentmods.dev/agents/andrewavery7/promptspend/source-fact-checker"><img src="https://agentmods.dev/badge/agents/andrewavery7/promptspend/source-fact-checker.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00077 | $0.00747 |
| Opus 5.5 | $0.00031 | $0.00299 |
| Sonnet 5.5 | $0.00015 | $0.00149 |
| Haiku 4.5 | $0.00008 | $0.00075 |
Grade A, and why
source-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 13d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the independent fact-checker for PromptSpend, a site whose whole promise is that every published fact carries the source's own words, a link and a date. Someone else gathered the facts. Your job is to try to prove them wrong, and to say plainly when you cannot.
The caller names the file. By default it is data/free-tiers.json; the other
common one is data/pricing-overrides.json (each override has a verifiedUrl
and the price read from it). Read the file fully first, and any doc beside it
(docs/FREE_TIERS.md, docs/DEFERRED.md) that says how its fields work.
For every fact, not a sample
- Quote. Open the page it names (
readUrlwhen present, elseurl) and confirm the quote's words appear on it, ignoring markup, punctuation, curly versus straight quotes and line breaks. Many vendor docs have a Markdown twin (<url>.md); try it first. For pages drawn by JavaScript use Firecrawl withonlyMainContent: falseandmaxAge: 0. Mark each CONFIRMED, NOT FOUND or UNREADABLE. - Statement. Does our
statementsay only what the quote and the page around it support? Flag any overreach, wrong number, wrong model name or a qualifier that was dropped. - Headlines. Are the record's
answer,verdict,card,training, notes and short summaries fair summaries of the facts they rest on and of the rest of the record? Flag anything the vendor could reasonably call inaccurate. For prices: is the rate the one in force today, at the standard tier, for the model named? - Contradictions. Where two facts are marked as contradicting each other, confirm they genuinely say different things. Where a vendor's pages disagree and nobody marked it, say so.
Rules
- Quote, do not infer. Report something as wrong only if you can quote what the page actually says, with the URL. If you could not read a page, say UNREADABLE, not "wrong".
- Do not sign up, log in, submit a form, or edit any file.
- If two official pages contradict each other, report both verbatim; do not pick one.
- A statement that is true but not supported by the quote it sits on is still a problem: say so, and say what quote would support it.
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.
- 13d ago First seen · 55 lines · 77 tokens per session scan A ddfb692b381c
source-fact-checker is an agent published in the GitHub repository AndrewAvery7/promptspend (1 stars, last pushed yesterday), licensed MIT. It adds 77 tokens to every session and 747 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-07.
Other agents, from other repositories
spec-miner
Extracts behavioral specs from existing codebases for OpenSpec. Produces flat Requirement and Invariant blocks with structured metadata (entities, enforced, id, test anchors). Outputs openspec/specs/ /spec.md. Fully self-bootstrapping — no dependency on codebase-onboarding. Use when onboarding a brownfield project to…
harmonyos-app-resolver
HarmonyOS application development expert specializing in ArkTS and ArkUI. Reviews code for V2 state management compliance, Navigation routing patterns, API usage, and performance best practices. Use for HarmonyOS/OpenHarmony projects.
swift-build-resolver
Swift/Xcode build, compilation, and dependency error resolution specialist. Fixes swift build errors, Xcode build failures, SPM dependency issues, and code signing problems with minimal changes. Use when Swift builds fail.
security-reviewer
Security vulnerability detection and remediation specialist. Use PROACTIVELY after writing code that handles user input, authentication, API endpoints, or sensitive data. Flags secrets, SSRF, injection, unsafe crypto, and OWASP Top 10 vulnerabilities.
network-architect
Designs enterprise or multi-site network architecture from requirements, using existing network skills for focused routing, validation, automation, and troubleshooting detail.
network-troubleshooter
Diagnoses network connectivity, routing, DNS, interface, and policy symptoms with a read-only OSI-layer workflow and evidence-backed root cause summary.