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/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/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/tyrusrc/praetor/auth-payment-agent"><img src="https://agentmods.dev/badge/agents/tyrusrc/praetor/auth-payment-agent.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 | $0.00059 | $0.01604 |
| Opus 5.5 | $0.00024 | $0.00642 |
| Sonnet 5.5 | $0.00012 | $0.00321 |
| Haiku 4.5 | $0.00006 | $0.00160 |
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 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 — 107 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 (WebAuthn API 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
if surface == 'session':
# 14-point session-management checklist (auto_probe categories=["session_security"]
# covers the stateful contexts; run_flow drives the multi-client ones)
1. test_session_lifecycle(login,logout,protected) — token still valid post-logout? (#2)
2. JWT not revoked on logout — replay the JWT after logout (#14, test_jwt + replay)
3. session survives PASSWORD CHANGE — run_flow: loginA→loginB→change-pw(A)→replay(B) 200? (#1)
4. session ID NOT rotated on privilege gain (org-join/upgrade/2FA/admin-accept) (#11)
5. session fixation — pre-set ID unchanged after login? (#9)
6. unbounded lifetime / static remember-me — stale cookie still 200 after long idle (#12/#13)
7. reset token: reuse after success, and old token valid after a new request (analyze_reset_tokens) (#6/#7)
8. sensitive endpoint checks cookie PRESENCE not validity — replay a logged-out req in Repeater (#8)
9. concurrent-session cap bypass; back-button cache of sensitive pages (no-store) (#10/#3)
10. email-verification bypass/swap — verify-link for email A validates email B → pre-ATO (#4/#5)
if surface == 'registration':
# 22-point signup checklist — most classes route through auto_probe; the
# signup-specific logic bugs are called out.
1. duplicate registration / account overwrite — re-register existing email w/ new pw;
case-sensitivity shadow account (authentication:duplicate_registration_overwrite)
2. username -> route collision — register admin/login/api/index.php (access_control:username_route_collision)
3. weak password policy — password==username/email, top-10 weak (authentication:weak_password_policy)
4. server-side validation bypass — empty/short/malformed fields past the client rules (Repeater)
5. hidden/legacy signup endpoints — /api/v1/register /auth/create /mobile/register skip checks
6. mass assignment — auto_probe categories=["mass_assignment"] (isAdmin/role/plan/org/state/provider_id)
7. HPP — email=victim&email=attacker (test_parameter_pollution / hpp)
8. stored XSS in name/username/email fields (auto_probe xss stored)
9. rate-limit / OTP brute during signup (test_rate_limit); null-byte (%00) truncation in inputs
10. punycode/IDN-homograph email -> normalization ATO (unicode_normalization)
11. email-verification bypass (response/status manipulation, forced-browsing, stale-token swap)
12. session fixation / non-rotating token across signup->verify->login (surface 'session')
13. cross-account IDOR on onboarding endpoints — two fresh accounts, swap IDs (auth-tester)
14. large-input DoS; disposable-email allowed; signup form served over HTTP
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 Changed · +31 lines 44b0884cd0a1
- 1mo 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 (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 59 tokens to every session and 1,604 once invoked, about $0.0002 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
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-verdict-assessor
Role brief for the verdict-assessor agent — assigns a RequirementVerdict (MET / NOTMET / PARTIALLYMET / NOTAPPLICABLE / REQUIRESMANUALREVIEW) to a PCI SSS v2.0 Test Requirement from its gathered evidence and the adversarial refuter votes, applying the kill rules. Mounted by the workflow Assess/Verdict step.