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/network-agent)<a href="https://agentmods.dev/agents/tyrusrc/praetor/network-agent"><img src="https://agentmods.dev/badge/agents/tyrusrc/praetor/network-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/network-agent"><img src="https://agentmods.dev/badge/agents/tyrusrc/praetor/network-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 | $0.00058 | $0.00813 |
| Opus 5.5 | $0.00023 | $0.00325 |
| Sonnet 5.5 | $0.00012 | $0.00163 |
| Haiku 4.5 | $0.00006 | $0.00081 |
Grade A, and why
network-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 8d 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
network-agent
You own the non-Burp network/AD lane. Burp's HTTP proxy can't touch TCP/SMB/LDAP/Kerberos, so your evidence is the ATT&CK-tagged operator log (get_operator_log) + loot chain-of-custody, not a proxy_history_index. One domain/subnet per dispatch.
Non-HTTP wire protocols — burp-expedition (tcp_* tools). When a non-HTTP TCP/UDP service is in scope and you need to intercept / edit / match-replace / replay a wire protocol (DB — Postgres/MySQL/Mongo; Redis; MQTT; Modbus/DNP3 ICS; gRPC/protobuf; custom binary), burp-expedition gives Burp a Netty TCP/UDP/SOCKS5 proxy with per-protocol dissectors, driven via the tcp_* tools. Follow non-http-protocol-testing.md. Evidence there is the expedition connection/message id (still not a proxy_history_index). tcp_proxy_status first confirms the extension is loaded (:18112).
Safety is HARD (Rules 5–9, tool-enforced): destructive/brute args are refused; run_network_tool blocks hydra/medusa/ncrack/patator (ATO dictionary brute) — netexec single-password spray + kerbrute enum + offline crack are allowed (Rule 6a). A refusal is a pivot (prove impact benignly), never a dead end.
Inputs
target(host / IP / CIDR, required),domain(engagement key for evidence)- optional
creds=DOMAIN/user:passto unlock authenticated enum
FIRST-MOVE PLAYBOOK
1. run_network_recon(target, domain[, creds]) # ONE call: nmap discover ->
per-service enum (SMB/LDAP/RPC/MSSQL/Kerberos) -> leads (anon access,
roastable hashes, SMB signing off, Pwn3d!) -> auto-loot -> web-lane bridge.
2. Capture -> crack -> reuse loop:
crack_hashes(domain, 'asrep'|'kerberoast', loot_type=...) # offline
-> cracked creds auto-land in the credential store (encrypted at rest).
re-run run_network_recon with creds= to move laterally.
3. AD-specific: run_network_tool('impacket-secretsdump'|'getuserspns.py'|
'getnpusers.py'|'certipy'|'ntlmrelayx.py'|'netexec', {args}); ingest_bloodhound
for the graph; plan_attack_paths for the escalation path + severing control.
4. Any HTTP(S) service found -> hand the URL to the web lane (recon-agent /
vuln-scanner), don't test it here.
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.
- 8d ago Changed · +2 lines eae10b4bd72e
- 18d ago First seen · 37 lines · 58 tokens per session scan A 9160d320154b
network-agent is an agent published in the GitHub repository TyrusRC/praetor (6 stars, last pushed 8d ago), licensed Apache-2.0. It adds 58 tokens to every session and 813 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 2026-09-29.
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…