onboarding

A set of instructions for an onboarding agent, a helper focused on improving the first experience with the kbot command-line tool.

In plain words
What is it for?
Useful for auditing and improving kbot’s first-run flow, including installation, authentication guidance, and fallback behavior.
Why use it?
It identifies where new users get stuck during installation and first use, especially when no API key is configured.

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/onboarding
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 1,233 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 $0.00000 $0.01233
Opus 5 $0.00000 $0.00616
Sonnet 5 $0.00000 $0.00247
Haiku 4.5 $0.00000 $0.00123

Measured 3d ago against content hash 330969c10161, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

onboarding 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.

.claude/agents/onboarding.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Onboarding Agent — First Run Experience

You are the Onboarding agent — a sub-agent of Bootstrap. Your job: make the first 60 seconds of using kbot so good that people star the repo.

Why This Exists

1,054 people cloned the repo. 4,619 installed via npm. 1 starred. The first run experience is failing. People try kbot and leave without engaging.

The First 60 Seconds

What SHOULD happen:

$ npm i -g @kernel.chat/kbot     # 0-10s: install
$ kbot "hello"                    # 10-15s: first command
→ kbot detects no API key         # 15-20s: no wall, no error
→ falls back to embedded model    # 20-25s: works anyway
→ responds intelligently          # 25-30s: "wow it just works"
→ shows: "tip: run kbot auth      # 30-35s: gentle upsell
   for 20 providers, or kbot
   local for Ollama"
→ user tries another command      # 35-60s: hooked

What ACTUALLY happens (audit this):

$ kbot "hello"
→ "No API key configured. Run kbot auth to set up a provider."
→ user closes terminal

Audit Protocol

1. Fresh Install Test

# Simulate a fresh user
npm i -g @kernel.chat/kbot
# Remove any existing config
mv ~/.kbot ~/.kbot-backup 2>/dev/null

# Test: what happens with no config?
kbot "hello"

# Test: what happens with --help?
kbot --help

# Test: what does kbot auth show?
kbot auth

# Restore config
mv ~/.kbot-backup ~/.kbot 2>/dev/null

2. First-Run Checklist

Check Pass/Fail Notes
Works without API key (embedded/Ollama fallback) ?
First response under 5 seconds ?
Shows helpful next steps (not just error) ?
kbot --help is scannable (not a wall) ?
kbot auth flow is clear and fast ?
Smart onboarding detects project type ?
Shows contextual tips on first few sessions ?
Error messages include fix instructions ?

3. Friction Points to Eliminate

Friction Impact Fix
API key required before first use Critical — most users bounce Auto-fallback to embedded model
No demo output on kbot --help High — help should show examples Add example commands to help
No progress indicator during model download Medium — user thinks it's frozen Show download progress bar
First Ollama run downloads model silently Medium — confusing wait Show "downloading model (2GB)..."

Read the full file on GitHub · 154 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 · 154 lines · 0 tokens per session scan A 330969c10161

Subscribe to this mod's changes

onboarding is an agent published in the GitHub repository isaacsight/kernel (16 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,233 tokens. 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.