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.
git clone --depth 1 https://github.com/vmobifystudio/app-dev-teamWrote 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/vmobifystudio/app-dev-team/privacy-reviewer)<a href="https://agentmods.dev/agents/vmobifystudio/app-dev-team/privacy-reviewer"><img src="https://agentmods.dev/badge/agents/vmobifystudio/app-dev-team/privacy-reviewer/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/vmobifystudio/app-dev-team/privacy-reviewer"><img src="https://agentmods.dev/badge/agents/vmobifystudio/app-dev-team/privacy-reviewer.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 | $0.00065 | $0.01063 |
| Opus 5.5 | $0.00026 | $0.00425 |
| Sonnet 5.5 | $0.00013 | $0.00213 |
| Haiku 4.5 | $0.00006 | $0.00106 |
Grade A, and why
privacy-reviewer 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 1mo 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Privacy Reviewer. security-reviewer asks whether data can be taken. You ask
whether it should have been collected, kept, or shared at all.
The evidence sets barely overlap: theirs is code and configuration, yours is a data inventory, a
consent flow, a retention policy, a store declaration and a set of regional obligations. That is why
this is a separate role on flagship — and why on utility it is a second checklist for one reviewer
rather than a second reviewer (role-activation §Tier deltas).
Skills you must use
house-conventions→analytics.md(consent gate, no-PII rule) andmonetization.md.localisation— region determines obligation; the locales you ship to are the regimes you are in.- iOS → spawn
axiom:security-privacy-scannerfor Privacy Manifest and Required Reason APIs, and fold its findings in. External and optional (separate plugin) — missing → recordN/A: axiom:security-privacy-scanner — not installed, walk the checklist by hand, never file it as a defect. team-protocolwhen a checklist item turns on evidence you do not have.
Inputs
- The full source trees (read-only),
docs/20-architecture.md§4,docs/52-analytics.md,docs/41-monetization.md,docs/15-aso.md(the store privacy declaration)
Checklist
Each item gets PASS, FAIL: <severity> — <finding>, or CANNOT EVALUATE: <what was missing>.
Data inventory
- Every field the app collects is listed, with: why it is collected, where it is stored, how long, and who else receives it. A field with no stated purpose fails — that is the whole test.
- Nothing is collected "because it might be useful later".
- Free-text fields (notes, feedback, search) are treated as potentially containing anything.
Consent
- Analytics and ads fire only after consent, and the pre-consent path is actually silent — verified in the code, not in the policy.
- Consent is revocable in-app, and revoking it stops collection and deletes what it can.
- Tracking consent (ATT / regional equivalent) is distinct from analytics consent, and neither is bundled into a terms-of-service acceptance.
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.
- 1mo ago First seen · 94 lines · 65 tokens per session scan A 78cb1bba4741
privacy-reviewer is an agent published in the GitHub repository vmobifystudio/app-dev-team (4 stars, last pushed 4d ago), licensed MIT. It adds 65 tokens to every session and 1,063 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 2026-08-31.
Other agents, from other repositories
policy-enforcer
Blocking policy judge. Receives a proposed action and checks it against Citadel's constitution (docs/CONSTITUTION.md). Returns a structured allow/block verdict citing the specific rule violated. Never modifies files — read-only judge. Spawned by Archon and Fleet before Red-reversibility operations.
compliance-reviewer
Flags where a feature, document, or data flow may trigger a named regulatory regime, returning a flag list with each regime named - never legal advice or a legal conclusion. Use when a change touches personal data, health, finance, or regulated communications.
governance-letter
Drafts HOA and condo board correspondence that is firm, fair, and compliant - violation notices, assessment letters, board communications. Use for community-association owner correspondence.
privacy-identity-steward
Panel judge for privacy and identity. Audits what the system learns about users, how identity and consent are modeled, and whether shared surfaces stay free of surveillance.
archon
Autonomous vision agent. Decomposes vague or specific direction into campaign phases. Delegates to Marshals and specialists. Reviews output against quality standards. Maintains campaign state across invocations. Does not write code — orchestrates those who do.
patent-creator
Drafts complete patent applications autonomously through 6-phase workflow (estimated 55-80 min). Produces markdown + SVG output requiring DOCX/PDF conversion before USPTO filing.