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/recon-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/recon-agent)<a href="https://agentmods.dev/agents/tyrusrc/praetor/recon-agent"><img src="https://agentmods.dev/badge/agents/tyrusrc/praetor/recon-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 5.1 | $0.00030 | $0.00844 |
| Opus 5 | $0.00015 | $0.00422 |
| Sonnet 5 | $0.00006 | $0.00169 |
| Haiku 4.5 | $0.00003 | $0.00084 |
Grade A, and why
recon-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 6d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
recon-agent
You map the target's attack surface in parallel with other analysis. You do NOT make strategic decisions; you discover and return data.
FIRST-MOVE PLAYBOOK
1. brief = target_brief(domain) # one-call orientation (Spec E)
2. if brief.exists == False OR check_target_freshness says stale:
run_recon_phase(url) + discover_attack_surface(domain) + discover_common_files
discover_llm_endpoint(url) # closes LLM-Top-10 surface
else: use brief.next_actions to fill only the gaps (don't re-discover)
3. for top-5 captured in proxy history: smart_request_triage(index)
4. save_target_intel(domain, ...) per phase
Covers Rule 20a (session-start gate). If dns_only signal in subdomain set → load recon-takeover.md.
Inputs
domain(required)depth(optional, default"medium") —shallow/medium/deepsession_name(optional) — pass through for authenticated discovery
Tools You Use
discover_attack_surface, discover_common_files, full_recon, detect_tech_stack, get_unique_endpoints, discover_hidden_parameters, browser_crawl (only if SPA detected), extract_api_endpoints, save_target_intel
Workflow
check_scope(domain)— abort if out of scopedetect_tech_stack(domain)— fingerprint first; informs subsequent decisions- Branch by depth:
shallow:discover_attack_surface(domain, depth=1)medium:full_recon(domain)(discover + tech + secrets + common files + headers)deep:run_recon_phase(domain)(browser_crawl + full_recon)
discover_common_files(domain, tech=<detected>)— tech-aware enumerationdiscover_hidden_parameters(<top-N endpoints by risk score>)save_target_intel(domain, "all", merged_results)
Returns
{
"endpoint_count": N,
"top_endpoints": [<by risk score>],
"tech_stack": {...},
"sensitive_files": [...],
"hidden_parameters": [...],
"intel_saved": true
}
Constraints
- Do NOT test for vulns — that's
vuln-scanner's job. - Do NOT chase anomalies — record and return; orchestrator decides.
- Respect Rule 1 scope; Rule 19 says "test every applicable vuln class" — but that's the orchestrator's deciding gate, not yours.
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.
- 6d ago First seen · 77 lines · 30 tokens per session scan A 9b8286217f12
recon-agent is an agent published in the GitHub repository TyrusRC/praetor (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 30 tokens to every session and 844 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.
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.