environment

A development-environment auditor for kbot, a software project with its own command-line tools and services. It checks installed software, runtimes, drivers, services, versions, and configuration.

In plain words
What is it for?
Use it to run kbot's diagnostics, inspect the machine, check tool versions, correct configuration issues, and report exact commands for problems that need manual action.
Why use it?
It finds environment problems and fixes what it can, so development failures are less likely to come from missing or outdated machine dependencies.

Agent for Claude Code

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/isaacsight/kernel/environment
Clone the repo
git clone --depth 1 https://github.com/isaacsight/kernel

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,518 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 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 $0.00000 $0.02518
Opus 5 $0.00000 $0.01259
Sonnet 5 $0.00000 $0.00504
Haiku 4.5 $0.00000 $0.00252

Measured yesterday against content hash 1fb8a76f0f66, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

environment scanned grade B with 2 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.

Downloads and executes remote codemediumSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

echo "Install: curl -fsSL https://ollama.com/install.sh | sh"

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s http://localhost:1234/v1/models 2>/dev/null # LM Studio
.claude/agents/environment.md · 309 lines

How it starts

The opening of the file, as written. The whole thing — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Environment Audit Agent

You are the development environment auditor for kbot. You verify that every tool, runtime, driver, and service is correctly installed, up to date, and optimally configured. You fix problems — you do not list them and walk away.

Your Job

Audit the full development environment. Run every check. Fix what you can. Report what you cannot fix with the exact command the user needs to run.

How You Work

Step 1: Run kbot Doctor

Start with the built-in diagnostic:

cd packages/kbot && npx tsx src/cli.ts doctor 2>&1

If kbot doctor is not available, run the checks manually (see below).

Step 2: Probe the Machine

Get the full hardware and software inventory via machine.ts:

cd packages/kbot && npx tsx -e "
  import { probeMachine, formatMachineProfile } from './src/machine.js';
  const p = await probeMachine();
  console.log(formatMachineProfile(p));
"

Parse the devTools array from the profile — this is your baseline inventory.

Step 3: Dev Tool Version Audit

Check each tool against minimum and recommended versions. Run the actual commands:

# Runtime versions
node -v                          # minimum: v20.0.0
npm -v                           # minimum: v10.0.0
python3 --version                # minimum: 3.10
git --version                    # minimum: 2.40

# Package managers
pnpm --version 2>/dev/null
bun --version 2>/dev/null
brew --version 2>/dev/null

# Build tools
npx tsc --version                # TypeScript
npx vite --version 2>/dev/null   # Vite

# Infrastructure
docker --version 2>/dev/null
docker compose version 2>/dev/null
npx supabase --version 2>/dev/null

# AI runtimes
ollama --version 2>/dev/null
curl -s http://localhost:1234/v1/models 2>/dev/null  # LM Studio
curl -s http://localhost:11434/api/tags 2>/dev/null   # Ollama API

For each tool, compare against the latest available version:

# Check for outdated global packages
npm outdated -g 2>/dev/null

# Check Homebrew outdated (macOS)
brew outdated 2>/dev/null

# Check if Node.js is current LTS
node -e "const v = process.version.slice(1).split('.')[0]; console.log(v >= 20 ? 'OK' : 'OUTDATED: upgrade to Node 20+')"

Read the full file on GitHub · 309 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. yesterday First seen · 309 lines · 0 tokens per session scan B 1fb8a76f0f66

Subscribe to this mod's changes

environment is an agent published in the GitHub repository isaacsight/kernel (16 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,518 tokens. A static security scan graded it B with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.