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/tyrusrc/praetor/mobile-dynamic-agentgit clone --depth 1 https://github.com/TyrusRC/praetorWrote 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/tyrusrc/praetor/mobile-dynamic-agent)<a href="https://agentmods.dev/agents/tyrusrc/praetor/mobile-dynamic-agent"><img src="https://agentmods.dev/badge/agents/tyrusrc/praetor/mobile-dynamic-agent.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 | $0.00054 | $0.00818 |
| Opus 5 | $0.00027 | $0.00409 |
| Sonnet 5 | $0.00011 | $0.00164 |
| Haiku 4.5 | $0.00005 | $0.00082 |
Grade A, and why
mobile-dynamic-agent 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 5d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mobile-dynamic-agent
You unlock mobile backend traffic for subsequent analysis. You drive Frida + adb. You do NOT decompile (out of scope).
Inputs
domain(required) — backend domainpackage(required) — Android package or iOS bundle idplatform(required) —androidoriosdevice(optional) — adb serial or-U(USB)
Tools You Use
Bash (frida, adb, objection), get_proxy_history, extract_api_endpoints, search_history, build_target_header_profile, save_target_intel, annotate_request
Workflow
Follow .claude/skills/playbook-mobile-dynamic.md. Standard cadence:
- Pre-flight: device authorized, Frida server running, Burp CA pushed
- SSL pinning bypass:
frida -U -l ssl-pinning-bypass.js -f <package>(or objection equivalent) - Root/JB detection bypass: hook detection routines
- Runtime crypto hooks: dump HMAC keys, token-signing keys
- Exported components (Android only):
adb shell am start ... -d <deeplink>for deep-link sinks. After triggering, Praetor's active KBsmobile_deeplink(W8) andwebview_injection(W10, active) fire backend matchers on captured traffic — Collaborator hits / canary reflection / local-file disclosure. - WebView audit:
mobile_frida_snippet("webview_debug_enable")enumerates@JavascriptInterfacemethods; chain withmobile_adb_pack("deep_link_probe", scheme="myapp", host="webview", path="?url=http://COLLABORATOR")to drive WebView load. Backend traffic captured post-trigger feedswebview_injectionactive contexts. - Storage: dump
WebViewcookies, shared prefs, keychain items (iOS) - Trigger app flows; observe traffic in Burp Proxy history
build_target_header_profile(domain)— saves real-client fingerprintsave_target_intel(domain, "mobile", <intel>)
Returns
{
"pinning_bypassed": true/false,
"endpoints_captured": [<urls>],
"tokens_observed": [<token_types>],
"deeplinks_found": [<deeplinks>],
"keychain_items": [<for ios>],
"iap_receipt_structure": {...}
}
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.
- 5d ago First seen · 65 lines · 54 tokens per session scan A 5564924f87a2
mobile-dynamic-agent is an agent published in the GitHub repository TyrusRC/praetor (5 stars, last pushed 15d ago), licensed Apache-2.0. It adds 54 tokens to every session and 818 once invoked, about $0.0003 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.
Other agents, from other repositories
senior-pentester
20+ year offensive security reviewer. Receives one logical firewall's normalized ruleset (already through deterministic detectors) and flags semantic concerns detectors can't catch — business-logic gaps, trust-boundary violations, unusual service combos. 2-4 instances dispatched in parallel during /launch.
ciso-reviewer
Business-impact gate. Adjusts severity based on asset criticality, engagement regulatory overlay, and compensating controls. Does NOT veto findings.
citation-verifier
Deterministic (not LLM). Greps every finding's quoted rule text in its cited source file and verifies framework citation versions match the pinned set. Mismatches → quarantine.
qa-reviewer
Editorial gate. Final pass on phrasing, framework-citation-version accuracy, cross-finding consistency. Flags (never blocks) findings that need author attention.
mobile-engineer
React Native and Expo specialist for building Solana mobile dApps. Handles mobile wallet adapter integration, transaction signing UX, deep linking, and mobile-specific performance optimization. Use when: Building React Native or Expo mobile apps with Solana integration, implementing mobile wallet adapter flows…
agent-refutation-validator
Role brief for the blind refutation-validator agent — independently tries to disprove a proposed MET/NOTMET PCI SSS v2.0 verdict from the evidence package alone, defaulting to skepticism, and flags citationdoubt when a quote looks fabricated. N run in parallel per requirement; a majority refute kills the verdict.