environment-detection

A setup check that scans a computer for installed AI command-line tools, required utilities, and Claude Code plugins.

In plain words
What is it for?
Use it to detect Gemini, Codex, and Claude versions and locations, check for jq, discover installed Claude Code plugins, and guide fallback behaviour.
Why use it?
It shows what the local environment can support and identifies missing tools or plugin conflicts before other workflows depend on them.

Skill for Claude CodeCodex

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 skills/joshidikshant/devsquad/environment-detection
Any agent
npx skills add joshidikshant/devsquad --skill environment-detection
Clone the repo
git clone --depth 1 https://github.com/joshidikshant/devsquad

Made for: Claude Code, Codex.

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,607 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 $0.00062 $0.02607
Opus 5 $0.00031 $0.01303
Sonnet 5 $0.00012 $0.00521
Haiku 4.5 $0.00006 $0.00261

Measured 2d ago against content hash a74ac7c0ab38, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

environment-detection 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.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/detect-environment.sh, scripts/detect-plugins.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugin/skills/environment-detection/SKILL.md · 237 lines

How it starts

The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Environment Detection Skill

Detect the developer's AI tooling landscape to determine which CLIs are installed, which plugins are active, and what degradation strategies are needed. This skill forms the foundation of DevSquad's onboarding flow and is invoked automatically during setup or on demand when the user wants to understand their current tooling.

Overview

DevSquad relies on external AI CLIs (Gemini, Codex) for delegation. Not every developer has all tools installed. This skill scans the environment to discover what is available, maps installed Claude Code plugins to avoid conflicts, and produces structured JSON reports that other skills and commands consume.

The detection covers three areas:

  1. CLI availability -- Which of the three AI CLIs (gemini, codex, claude) are installed, where they are located, and what versions they report.
  2. Dependency checking -- Whether critical utilities like jq are present for full functionality.
  3. Plugin discovery -- Which Claude Code plugins are installed, their command namespaces, and whether they conflict with DevSquad.

The output of this skill drives the delegation engine. If Gemini is missing, research tasks cannot be delegated to it. If Codex is missing, boilerplate generation stays with Claude. The skill quantifies exactly what the developer can and cannot do.

Detection Process

To run environment detection, execute the following scripts via the Bash tool. Both scripts output JSON to stdout and warnings to stderr.

Step 1: Detect AI CLIs

Execute the environment detection script:

bash "${CLAUDE_PLUGIN_ROOT}/skills/environment-detection/scripts/detect-environment.sh"

If CLAUDE_PLUGIN_ROOT is not set, the script resolves the plugin root from its own location automatically.

The script performs the following operations:

  1. Sources lib/cli-detect.sh from the plugin root to get base detection functions.
  2. Checks availability of gemini, codex, and claude using command -v (POSIX portable, no reliance on which).
  3. Records the full path to each CLI binary.
  4. Attempts version detection with a 5-second timeout per CLI. Uses gtimeout on macOS if available, falls back to timeout on Linux, and skips version detection gracefully if neither exists.
  5. Checks for jq availability as a dependency.
  6. Computes a summary: which agents are available, which are missing, whether delegation is possible, and whether the environment is degraded.

Read the full file on GitHub · 237 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 237 lines · 62 tokens per session scan A a74ac7c0ab38

Subscribe to this mod's changes

environment-detection is a skill published in the GitHub repository joshidikshant/devsquad (7 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 2,607 once invoked, about $0.0003 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 skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens