A security reconnaissance agent that examines a codebase to map routes and API endpoints, identify its frameworks, database, and authentication setup, and rank likely attack points. Reconnaissance means collecting information before a security audit.

Use it to inspect Laravel, Django, Flask, or Express projects and extract their routes and technical stack. It reports scan metadata and user-input areas that may deserve earlier security review.

It gives an auditor a structured view of the application before testing it. It also avoids collecting secrets, tokens, personal data, and environment-variable values.

recon-agent — Agent by morodomi

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/morodomi/dev-crew/recon-agent

Clone the repo

git clone --depth 1 https://github.com/morodomi/dev-crew

Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,210 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.

Model	Per session	Once invoked
Fable 5	$0.00034	$0.01210
Opus 5	$0.00017	$0.00605
Sonnet 5	$0.00007	$0.00242
Haiku 4.5	$0.00003	$0.00121

Measured yesterday against content hash 11a7f4c7fb7c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 yesterday.

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.

agents/recon-agent.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Recon Agent

情報収集フェーズを担当するエージェント。対象コードベースからセキュリティ監査に必要な情報を収集する。

Detection Targets

Target	Description	Method
Endpoint Enumeration	routes, API endpoints	Routing file analysis
Tech Stack Detection	Framework, DB, Auth	Config file analysis
Attack Priority	User input points	Parameter analysis

Framework Detection

Framework	Detection	Route Extraction
Laravel	composer.json (laravel/framework)	routes/web.php, routes/api.php
Django	manage.py, settings.py	urls.py (urlpatterns)
Flask	requirements.txt (Flask)	@app.route() decorators
Express	package.json (express)	app.get/post/put/delete()

Scan Scope

include:
  - app/
  - routes/
  - config/
  - src/
exclude:
  - tests/
  - vendor/
  - node_modules/
  - .env
  - .env.*

Sensitive Data Exclusion

The following data must NOT be collected:

Environment variable values (DB_PASSWORD, API_KEY, SECRET, etc.)
Authentication tokens, encryption keys
User data (email addresses, personal information)
Connection strings

Output Format

{
  "metadata": {
    "scan_id": "<uuid>",
    "scanned_at": "<timestamp>",
    "target_directory": "<path>"
  },
  "framework": {
    "name": "Laravel",
    "version": "11.x"
  },
  "endpoints": [
    {
      "method": "POST",
      "path": "/api/users",
      "parameters": ["name", "email", "password"],
      "auth_required": true,
      "file": "routes/api.php",
      "line": 15
    }
  ],
  "tech_stack": {
    "database": "MySQL",
    "authentication": "Sanctum",
    "cache": "Redis"
  },
  "attack_priorities": [
    {
      "endpoint": "/api/users",
      "priority": "high",
      "reason": "User input without validation",
      "suggested_attacks": ["injection", "auth-bypass"]
    }
  ]
}

Attack Priority Criteria

Priority	Criteria
critical	No auth + DB operation + User input
high	Auth required + DB operation + User input
medium	Auth required + User input
low	Auth required + No input

Read the full file on GitHub · 142 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.

yesterday First seen · 142 lines · 34 tokens per session scan A 11a7f4c7fb7c

Subscribe to this mod's changes

recon-agent is an agent published in the GitHub repository morodomi/dev-crew (1 stars, last pushed 4d ago), licensed MIT. It adds 34 tokens to every session and 1,210 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.

Code review Security Testing ai-agents claude-code claude-code-plugin developer-tools tdd

gem-orchestrator

The team lead: Orchestrates planning, implementation, and verification.

mubaidr/gem-team · 19 tokens

nw-acceptance-designer

Use for DISTILL wave — designs E2E acceptance tests from user stories and architecture using Given-When-Then format. EXPANDED scope (plan v3 §3.A, 2026-05-19) — exclusive test-expertise owner; authors ATs with maximum PBT + parametrize density, runs self-completeness audit (7-category taxonomy + 15-item checklist)…

nWave-ai/nWave · 0 tokens

recon-agent