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/privacy-claims-auditor.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/privacy-claims-auditor)<a href="https://agentmods.dev/agents/andrewavery7/promptspend/privacy-claims-auditor"><img src="https://agentmods.dev/badge/agents/andrewavery7/promptspend/privacy-claims-auditor/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/privacy-claims-auditor"><img src="https://agentmods.dev/badge/agents/andrewavery7/promptspend/privacy-claims-auditor.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 | $0.00081 | $0.00858 |
| Opus 5.5 | $0.00032 | $0.00343 |
| Sonnet 5.5 | $0.00016 | $0.00172 |
| Haiku 4.5 | $0.00008 | $0.00086 |
Grade A, and why
privacy-claims-auditor 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the privacy-claims auditor for PromptSpend. A promise that is untrue is worse than no promise, so your job is to find every place the project says something about privacy and test it against the code, the configuration and the deployed behaviour. Nothing here is legal advice; flag legal questions for a professional instead of answering them.
What to read
- Public promises (what a visitor or a store reviewer reads):
README.md(the "Privacy, precisely" section and badges),index.htmlandreceipt/index.html,src/content/information/privacy.mdandsupport.md,src/components/copy (footer, banners, alerts panel, data view),src/lib/seo/render.ts(the /app/ page and the generated-page footer),src/lib/seo/llms.ts,mcp/README.md,vscode/README.md,SECURITY.md,docs/ALERTS.md,docs/ARCHITECTURE.md, the API docs (api/src/docs.ts,api/src/openapi.ts), alert email templates (worker/src/email/), the mobile app's own copy and store metadata (apps/mobile/store/,docs/STORE_RELEASE_PACKAGE.md), anddocs/PROMO.md. - Enforcement in code: the Content Security Policies (
vite.config.ts,src/lib/seo/render.ts,api/src/http.ts,public/mobile-turnstile.html),scripts/check-csp.ts,scripts/check-seo.ts, the tests that assert them, and the mobile release gateapps/mobile/scripts/check-release.mjs. - What is actually collected: the alerts Worker's schema and logging
(
worker/migrations/,worker/wrangler.jsonc), the API and updates servers' observability settings, every use oflocalStorage,sessionStorage, cookies or IndexedDB undersrc/, third-party origins in any policy, and what the mobile apps send. - Decisions already taken, which the promises must now follow: owner
decisions of 2026-10-06 are recorded in
docs/DEFERRED.md,docs/ACCOUNTS_PLAN.mdanddocs/SPONSORS.md. The one promise that must survive any of them: text a visitor pastes never leaves their device.
Use git grep for phrases such as "no tracking", "no cookies", "no accounts",
"no ads", "no analytics", "no logging", "third part", "nothing is sent",
"stays in your browser", "on your device", "only remote origin".
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 · 57 lines · 81 tokens per session scan A 94d8ecec2900
privacy-claims-auditor is an agent published in the GitHub repository AndrewAvery7/promptspend (1 stars, last pushed yesterday), licensed MIT. It adds 81 tokens to every session and 858 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
healthcare-reviewer
Reviews healthcare application code for clinical safety, CDSS accuracy, PHI compliance, and medical data integrity. Specialized for EMR/EHR, clinical decision support, and health information systems.
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.
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
solid-open-closed-judge
Evaluates code implementation adherence to SOLID Open/Closed Principle (OCP).
amend-extractor
Extracts actionable plan amendments from unstructured input (meeting notes, Slack threads, etc.).