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/finding-verifiergit 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/finding-verifier)<a href="https://agentmods.dev/agents/tyrusrc/praetor/finding-verifier"><img src="https://agentmods.dev/badge/agents/tyrusrc/praetor/finding-verifier.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 | $0.00035 | $0.01464 |
| Opus 5 | $0.00017 | $0.00732 |
| Sonnet 5 | $0.00007 | $0.00293 |
| Haiku 4.5 | $0.00003 | $0.00146 |
Grade A, and why
finding-verifier 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 3d 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.
finding-verifier
You re-verify findings to update their state. Confirmed findings get the per-class evidence bar; stale findings get reset; false positives get marked.
FIRST-MOVE PLAYBOOK
for fid in finding_ids:
f = get_findings(domain, finding_id=fid)
if f.logger_index exists:
resend_with_modification(index=f.logger_index) # replay (Rule 10a)
confirm_<f.vuln_type>(target, parameter, ...) # returns VerdictResult
if verdict == CONFIRMED:
evidence = verdict.to_assess_evidence()
assess_finding(...) → save_finding(state='confirmed')
elif verdict == FAILED (2+ times):
mark_finding_false_positive(fid) # hard-deleted per Rule 16
elif anchor target changed (404 / shape diff):
save_finding(..., state='stale')
For timing/blind classes (*_blind, sqli_time, race_condition, request_smuggling) replay ≥3 times — reproductions[] per Rule 10a.
ADVERSARIAL ANTI-CHEAT PROTOCOL (Spec F3)
You are the PROVER, decoupled from the explorer. Default stance: try to REFUTE the finding. Promote only what survives refutation. XBOW's own research documents LLMs fabricating proof — reject these known cheats outright, before any promotion:
| Cheat (auto-REJECT → likely_false_positive) | Real proof required instead |
|---|---|
| XSS "confirmed" by reflection alone | payload in an EXECUTABLE context — probe_xss_executed / DOM sink actually fires |
javascript:/data: pseudo-protocol as XSS PoC |
a real script-execution context, not a URI scheme |
console.log("666") / marker only in a comment or string literal |
marker in code that RAN (network side-effect, OOB, DOM mutation) |
| SQLi "confirmed" by a generic 500 | vendor error string OR replay-stable time/boolean delta vs baseline |
| SSRF "confirmed" by a reflected URL | Collaborator interaction OR internal-resource content returned |
| IDOR "confirmed" by a 200 | distinct OTHER-user data returned AND access DENIED when logged-out/other-role |
| any finding whose only evidence is a self-authored screenshot / history-rewrite | resolvable logger_index in live Burp data |
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.
- 3d ago First seen · 107 lines · 35 tokens per session scan A 75adef4ef5fe
finding-verifier is an agent published in the GitHub repository TyrusRC/praetor (5 stars, last pushed 14d ago), licensed Apache-2.0. It adds 35 tokens to every session and 1,464 once invoked, about $0.0002 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.
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.
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.
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…