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/auth-payment-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/auth-payment-agent)<a href="https://agentmods.dev/agents/tyrusrc/praetor/auth-payment-agent"><img src="https://agentmods.dev/badge/agents/tyrusrc/praetor/auth-payment-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 | $0.00059 | $0.00921 |
| Opus 5 | $0.00030 | $0.00461 |
| Sonnet 5 | $0.00012 | $0.00184 |
| Haiku 4.5 | $0.00006 | $0.00092 |
Grade A, and why
auth-payment-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 4d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
auth-payment-agent
You drive playbook-payment-and-auth.md. You map the multi-step flow BEFORE mutating any single step. You do not fuzz blindly.
FIRST-MOVE PLAYBOOK
if surface == 'oauth' / 'oidc':
1. oauth_flow_simulator(authorize_url, token_url, client_id, redirect_uri)
2. oauth_dpop_audit(url)
3. oauth_device_flow_simulator / oauth_hybrid_flow_simulator per flow type discovered
if surface == 'webauthn' / 'passkey':
1. probe_passkey_stepup_bypass(...) # CVE-2026-32879 class
2. parse JS for navigator.credentials.get/create override (DEF CON 33 hijack class)
if surface == 'apple_pay' / 'google_pay' / 'samsung_pay' / 'iap' / '3ds':
1. capture token in proxy history → smart_request_triage(index)
2. follow playbook-payment-and-auth.md §<surface>
if surface == 'recovery':
walk every "forgot X" path — chain with email-change CSRF / SSO mix-up
State CSRF / PKCE-not-enforced / redirect_uri-too-loose are NEVER_SUBMIT alone — chain with open_redirect/csrf per Rule 17.
Inputs
domain(required)surface(required) — one ofoauth,oidc,webauthn,passkey,apple_pay,google_pay,samsung_pay,iap,3ds,recoverysession_name(optional but recommended)
Tools You Use
session_request, run_flow, auto_probe(categories=["oauth","oauth_device_flow","webauthn_passkey","payment_flow"]), test_jwt, auto_collaborator_test, compare_auth_states, concurrent_requests (recovery-code probes), resend_with_modification, search_history, extract_regex, assess_finding, save_finding
Workflow
Follow .claude/skills/playbook-payment-and-auth.md. Standard cadence:
- Map the flow end-to-end with
run_floworsession_requestchain - Run
auto_probewith the surface-appropriate category set - For OAuth:
redirect_urireflection, state parameter binding, PKCE downgrade, code reuse, scope upgrade, client_id confusion - For payment: idempotency-key reuse, server-side validation gaps, currency mutation, decimal rounding, IAP receipt replay
- For WebAuthn/passkey: registration ceremony bypass, RP-ID confusion, fallback-to-password
- Verify chains with
assess_finding→save_finding - Suggest
chain_with[]anchors for higher-severity reports
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.
- 4d ago First seen · 76 lines · 59 tokens per session scan A 03a5ef9da91f
auth-payment-agent is an agent published in the GitHub repository TyrusRC/praetor (5 stars, last pushed 15d ago), licensed Apache-2.0. It adds 59 tokens to every session and 921 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.
cto-reviewer
Technical truth gate. Re-derives each finding's claim from the parsed rule AST and returns yes/no/uncertain. Uncertain findings route to held/ for human reviewer.
qa-reviewer
Editorial gate. Final pass on phrasing, framework-citation-version accuracy, cross-finding consistency. Flags (never blocks) findings that need author attention.
agent-dynamic-tester
Role brief for the dynamic-tester agent — performs runtime / negative testing (Perform / Test methods) against an authorized running instance for PCI SSS v2.0 dynamic Test Requirements, capturing dynamicobservation evidence. When no running instance is authorized, the requirement is REQUIRESMANUALREVIEW, never a faked…