recon-agent

recon-agent is an agent for Claude Code from TyrusRC/praetor. It costs 30 tokens per session (844 once invoked), scanned A, original, Apache-2.0.

A cybersecurity reconnaissance agent that maps a website or application’s exposed entry points, technology, sensitive files, and hidden inputs. Reconnaissance is the information-gathering phase of a security assessment.

In plain words
What is it for?
Finding endpoints, common files, API routes, hidden parameters, technologies, and possible language-model endpoints, then saving the findings for later analysis.
Why use it?
It collects an organized picture of the target before deeper security analysis begins, reducing repeated discovery work.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions Claude Code; mentions AGENTS.md.

Install

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.

agentmods
npx agentmods add agents/tyrusrc/praetor/recon-agent
Clone the repo
git clone --depth 1 https://github.com/TyrusRC/praetor

Made for: Claude Code.

Wrote 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.

agentmods badge for recon-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/tyrusrc/praetor/recon-agent.svg)](https://agentmods.dev/agents/tyrusrc/praetor/recon-agent)
Your own site
<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>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 844 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 6d ago against content hash 9b8286217f12, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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.

.claude/agents/recon-agent.md · 77 lines

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/deep
  • session_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

  1. check_scope(domain) — abort if out of scope
  2. detect_tech_stack(domain) — fingerprint first; informs subsequent decisions
  3. 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)
  4. discover_common_files(domain, tech=<detected>) — tech-aware enumeration
  5. discover_hidden_parameters(<top-N endpoints by risk score>)
  6. 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.

Read the full file on GitHub · 77 lines

Changes

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.

  1. 6d ago First seen · 77 lines · 30 tokens per session scan A 9b8286217f12

Subscribe to this mod's changes

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.

Related

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.

transilienceai/communitytools · 62 tokens

ciso-reviewer

Business-impact gate. Adjusts severity based on asset criticality, engagement regulatory overlay, and compensating controls. Does NOT veto findings.

transilienceai/communitytools · 32 tokens

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.

transilienceai/communitytools · 41 tokens

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.

transilienceai/communitytools · 40 tokens

qa-reviewer

Editorial gate. Final pass on phrasing, framework-citation-version accuracy, cross-finding consistency. Flags (never blocks) findings that need author attention.

transilienceai/communitytools · 35 tokens

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.

transilienceai/communitytools · 82 tokens