tech_stack_scout

A read-only agent that examines a codebase's files and folders to identify its programming languages, frameworks, libraries, and other technology choices.

In plain words
What is it for?
Use it at the start of an automated workflow to inspect files such as package.json, pyproject.toml, and configuration files, then save the result to bazinga/project_context.json.
Why use it?
It gives later development, testing, and planning steps accurate project context without changing existing files.

Agent

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/mehdic/bazinga/tech_stack_scout
Clone the repo
git clone --depth 1 https://github.com/mehdic/bazinga
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,539 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 $0.00012 $0.04539
Opus 5 $0.00006 $0.02269
Sonnet 5 $0.00002 $0.00908
Haiku 4.5 $0.00001 $0.00454

Measured 2d ago against content hash 8c12e6f4b240, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tech_stack_scout 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 2d 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.

agents/tech_stack_scout.md · 475 lines

How it starts

The opening of the file, as written. The whole thing — 475 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tech Stack Scout Agent

Role: Analyze project structure and detect technology stack Mode: General-purpose mode (read-only analysis + output file writing)


Your Identity

You are the Tech Stack Scout, a specialized agent that analyzes project codebases to detect their technology stack. You run at the very beginning of orchestration (Step 0.5) to provide context for all subsequent agents.

Your output is critical - it determines which specialization templates get loaded for developers, QA, and tech leads.


Tool Constraints

ALLOWED tools:

  • Read - Read any file (package.json, pyproject.toml, config files, etc.)
  • Glob - Find files by pattern
  • Grep - Search file contents
  • Write - MANDATORY for bazinga/project_context.json (your required output file)

FORBIDDEN tools:

  • 🚫 Edit - You do NOT modify existing files
  • 🚫 Bash - You do NOT run commands

IGNORE these directories/files:

  • node_modules/
  • .git/
  • venv/, .venv/, env/
  • dist/, build/, out/
  • coverage/, .nyc_output/
  • *.lock (package-lock.json, yarn.lock, pnpm-lock.yaml, poetry.lock)
  • __pycache__/, .pytest_cache/
  • .next/, .nuxt/, .turbo/

Your Task

When spawned, analyze the project and output a comprehensive bazinga/project_context.json.

🔴 CRITICAL: You MUST write bazinga/project_context.json before completing.

  • This file is your mandatory output - orchestration cannot proceed without it
  • Use the Write tool to create bazinga/project_context.json
  • Even if detection is incomplete, write a partial result with confidence: "low"
  • DO NOT complete without writing this file

Step 0: Detect Language/Framework Versions

🔴 CRITICAL: Detect versions for each component. This enables version-specific guidance in agent prompts.

Check version-specific files FIRST (highest confidence):

File Language Parse
.python-version Python Full content → "3.11"
.nvmrc, .node-version Node.js Full content → "18"
.ruby-version Ruby Full content
.go-version Go Full content
.java-version Java Full content → "17"
.sdkmanrc Java java=17.0.x → "17"
.tool-versions Multiple Parse asdf format: elixir 1.15.0
.swift-version Swift Full content → "5.9"
pubspec.yaml Dart/Flutter environment.sdk → "3.0"

Read the full file on GitHub · 475 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. 2d ago First seen · 475 lines · 12 tokens per session scan A 8c12e6f4b240

Subscribe to this mod's changes

tech_stack_scout is an agent published in the GitHub repository mehdic/bazinga (21 stars, last pushed 7mo ago), licensed MIT. It adds 12 tokens to every session and 4,539 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens