stack-detector

stack-detector is an agent for coding agents from MadAppGang/claude-code. It costs 17 tokens per session (5,888 once invoked), scanned A, original, MIT.

A project-analysis agent that detects the technologies used in a codebase and finds relevant Claude Code skills. It can identify multiple parts of a project, such as a frontend and backend.

In plain words
What is it for?
Use it to scan configuration files and folders, identify all technology stacks, discover available skills, and produce a detection report.
Why use it?
It helps clarify what a project is built with and prevents useful project-specific skills from being overlooked.

Agent

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the dev plugin — 47 skills, 12 commands, 14 agents 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/madappgang/claude-code/stack-detector
Clone the repo
git clone --depth 1 https://github.com/MadAppGang/claude-code

Or install dev, the plugin that ships this one along with the rest of its 47 skills, 12 commands, 14 agents.

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 stack-detector

README.md
[![agentmods](https://agentmods.dev/badge/agents/madappgang/claude-code/stack-detector.svg)](https://agentmods.dev/agents/madappgang/claude-code/stack-detector)
Your own site
<a href="https://agentmods.dev/agents/madappgang/claude-code/stack-detector"><img src="https://agentmods.dev/badge/agents/madappgang/claude-code/stack-detector.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,888 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 $0.00017 $0.05888
Opus 5 $0.00009 $0.02944
Sonnet 5 $0.00003 $0.01178
Haiku 4.5 $0.00002 $0.00589

Measured 2d ago against content hash 8d8ae53a087b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

stack-detector 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.

plugins/dev/agents/stack-detector.md · 684 lines

How it starts

The opening of the file, as written. The whole thing — 684 lines — stays where its author put it; the contents beside it link to each section on GitHub.

  Before starting, create todo list:
  1. Scan config files
  2. Analyze directory structure
  3. Discover real project skills
  4. Map technologies to bundled skills
  5. Generate detection report

  Update continuously as you progress through phases.
</todowrite_requirement>

<multi_stack_detection>
  ALWAYS check for multiple stacks. A project may have:
  - Frontend (React, Vue) in root or /frontend directory
  - Backend (Go, Rust, Python, Bun) in root or /backend directory
  - Both (fullstack)

  Return ALL detected stacks, not just the first one found.

  Example fullstack project:
  - package.json with React → frontend stack
  - go.mod → backend stack
  - Result: "react-typescript + golang", mode: "fullstack"
</multi_stack_detection>

<output_requirement>
  When SESSION_PATH is provided, write results to ${SESSION_PATH}/context.json
  with this structure:

  ```json
  {
    "detected_stack": "react-typescript + golang",
    "mode": "fullstack",
    "stacks": ["react-typescript", "golang"],
    "discovered_skills": [
      {
        "name": "tdd-workflow",
        "description": "Test-driven development with red-green-refactor cycle",
        "path": ".claude/skills/tdd-workflow/SKILL.md",
        "source": "project",
        "categories": ["testing", "workflow"]
      },
      {
        "name": "api-contracts",
        "description": "OpenAPI-first API development",
        "path": ".claude/skills/api-contracts/SKILL.md",
        "source": "project",
        "categories": ["backend", "api"]
      }
    ],
    "bundled_skill_paths": [
      "${PLUGIN_ROOT}/skills/core/universal-patterns/SKILL.md",
      "${PLUGIN_ROOT}/skills/core/testing-strategies/SKILL.md",
      "${PLUGIN_ROOT}/skills/frontend/react-typescript/SKILL.md",
      "${PLUGIN_ROOT}/skills/frontend/state-management/SKILL.md",
      "${PLUGIN_ROOT}/skills/frontend/testing-frontend/SKILL.md",
      "${PLUGIN_ROOT}/skills/backend/golang/SKILL.md",
      "${PLUGIN_ROOT}/skills/backend/api-design/SKILL.md",
      "${PLUGIN_ROOT}/skills/backend/database-patterns/SKILL.md"
    ],
    "quality_checks": {
      "frontend": [
        "bun run format",
        "bun run lint",
        "bun run typecheck",
        "bun test"
      ],
      "backend": [
        "go fmt ./...",
        "go vet ./...",
        "golangci-lint run",
        "go test ./..."
      ]
    },
    "frameworks": {
      "react": "19.0.0",
      "go": "1.21"
    }
  }
  ```

  CRITICAL:
  - Use ${PLUGIN_ROOT} placeholder for bundled skill paths (expanded at runtime)
  - Use relative paths for discovered project skills (from project root)
  - discovered_skills contains REAL skills found in the target project
  - bundled_skill_paths contains skills from the dev plugin
</output_requirement>

</critical_constraints>

Read the full file on GitHub · 684 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 · 684 lines · 17 tokens per session scan A 8d8ae53a087b

Subscribe to this mod's changes

stack-detector is an agent published in the GitHub repository MadAppGang/claude-code (279 stars, last pushed 5mo ago), licensed MIT. It adds 17 tokens to every session and 5,888 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 2026-09-03.