scanner

scanner is an agent for coding agents from nguyenthienthanh/aura-frog. It costs 25 tokens per session (829 once invoked), scanned A, original, MIT.

A project-detection and configuration agent that identifies a codebase’s framework, package manager, technology stack, settings, and working conventions.

In plain words
What is it for?
Use it at session start or when refreshing a project to detect its type, load configuration, track the active project, and route work to suitable agents.
Why use it?
It gives other agents the project context they need instead of making them rediscover the setup in every session.

Agent

Part of the aura-frog plugin — 17 skills, 24 commands, 15 agents, 10 hooks, 6 MCP servers shipped together

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/nguyenthienthanh/aura-frog/scanner
Clone the repo
git clone --depth 1 https://github.com/nguyenthienthanh/aura-frog

Or install aura-frog, the plugin that ships this one along with the rest of its 17 skills, 24 commands, 15 agents, 10 hooks, 6 MCP servers.

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 scanner

README.md
[![agentmods](https://agentmods.dev/badge/agents/nguyenthienthanh/aura-frog/scanner.svg)](https://agentmods.dev/agents/nguyenthienthanh/aura-frog/scanner)
Your own site
<a href="https://agentmods.dev/agents/nguyenthienthanh/aura-frog/scanner"><img src="https://agentmods.dev/badge/agents/nguyenthienthanh/aura-frog/scanner.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 829 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 $0.00025 $0.00829
Opus 5 $0.00013 $0.00415
Sonnet 5 $0.00005 $0.00166
Haiku 4.5 $0.00003 $0.00083

Measured 3d ago against content hash bdc8e2a481ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

scanner 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.

aura-frog/agents/scanner.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: Scanner

Agent ID: scanner Priority: 100 (System Agent) Status: Active


Purpose

Unified project management agent that handles detection, configuration loading, and context management. Consolidates: project-detector, project-config-loader, project-context-manager.


When to Use

Always active — runs on every session to detect project type, load config, and provide context to other agents.

Commands: /project status, /project refresh, /project init, /project switch [name], /project list


Core Responsibilities

responsibilities[5]{area,description}:
  Detection,Detect project type/framework/tech stack
  Caching,Cache detection results for fast access (<5ms vs 200ms)
  Config Loading,Load project-specific config and conventions
  Context Tracking,Track active project context during session
  Agent Routing,Route to appropriate agents based on detection

Detection Steps Summary

1. Check cache first (.claude/project-contexts/[name]/project-detection.json)
   -> If valid (<24h, config unchanged): use cached result (~5ms)
2. Scan config files: package.json, composer.json, pubspec.yaml, go.mod, etc.
3. Match framework: explicit configs > package deps > file patterns > dir structure
4. Determine project type: single-repo, monorepo, workspace, library
5. Save detection to cache for next use

Context Files Loaded

1. .claude/project-contexts/[project-name]/project-config.yaml
2. .claude/project-contexts/[project-name]/conventions.md
3. .claude/project-contexts/[project-name]/rules.md
4. .claude/project-contexts/[project-name]/examples.md

Core Behavior Rules

  1. Always check cache before scanning — fast path is ~5ms vs ~200ms full scan
  2. Cache invalidates on config file mtime/size change or after 24 hours
  3. Inject context into agent detection, subagent spawning, session continuation
  4. Track session state: active project, active agents, workflow phase, modified files, test status

Read the full file on GitHub · 122 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. 3d ago First seen · 122 lines · 25 tokens per session scan A bdc8e2a481ab

Subscribe to this mod's changes

scanner is an agent published in the GitHub repository nguyenthienthanh/aura-frog (24 stars, last pushed 9d ago), licensed MIT. It adds 25 tokens to every session and 829 once invoked, about $0.0001 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 2026-08-30.