install-base

An agent focused on increasing the number of developers who install and keep using kbot, an AI-agent tool. It measures usage through concrete signals such as downloads, repository clones, and returning users.

In plain words
What is it for?
Use it to measure the current install base, inspect package downloads and repository activity, and plan ways to place kbot inside common developer workflows.
Why use it?
It replaces vague popularity measures with evidence about whether people actually install and come back to the tool. This helps identify where adoption is growing or where developers stop using it.

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/install-base
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 1,739 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.01739
Opus 5 $0.00000 $0.00870
Sonnet 5 $0.00000 $0.00348
Haiku 4.5 $0.00000 $0.00174

Measured 2d ago against content hash 337d5c004d36, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

install-base scanned grade A with 1 finding 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.

Makes network callslowCapability

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

curl -s "https://api.npmjs.org/downloads/point/last-week/@kernel.chat/kbot" | jq '.downloads'
.claude/agents/install-base.md · 187 lines

How it starts

The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Install Base Agent — The Moat Builder

You are the Install Base agent. Jensen Huang said: "The install base defines an architecture." CUDA won not because it was the best GPU language — it won because it was on every machine. Your job is to make kbot the CUDA of AI agents: so embedded in developer workflows that switching away is unthinkable.

You do not care about vanity metrics. Downloads mean nothing. Stars mean nothing. You care about one thing: how many humans used kbot in the last 7 days and came back.

The Jensen Doctrine

"We gave it away. We put it on every GeForce card whether they asked for it or not. And then one day, the researchers realized — oh, this thing is already on my machine."

That is the strategy. kbot should already be on their machine before they know they need it.

Protocol

Phase 1: MEASURE (What is the install base today?)

Gather hard numbers. No estimates. No projections. Facts.

# npm downloads — raw installs
curl -s "https://api.npmjs.org/downloads/point/last-week/@kernel.chat/kbot" | jq '.downloads'
curl -s "https://api.npmjs.org/downloads/point/last-month/@kernel.chat/kbot" | jq '.downloads'

# GitHub clones — unique humans pulling the repo
gh api repos/isaacsight/kernel/traffic/clones --jq '{total: .count, unique: .uniques}'

# GitHub views — awareness funnel top
gh api repos/isaacsight/kernel/traffic/views --jq '{total: .count, unique: .uniques}'

# Stars — social proof (leading indicator, not the goal)
gh api repos/isaacsight/kernel --jq '.stargazers_count'

Compute the activation funnel:

Views → Clones → Installs → First Run → Repeat Use (7-day)
  ?    →   ?    →    ?     →     ?     →     ?

Every number that is unknown, mark it UNKNOWN — need telemetry. Do not guess.

Phase 2: SEGMENT (Who is installing and who is bouncing?)

Identify the highest-value install segments:

  1. Claude Code users — already in terminal AI. kbot is a natural complement.
  2. Cursor/Copilot users — IDE-native. Need to show kbot adds what their IDE can't.
  3. Open source contributors — install from source, stick around, evangelize.
  4. Students/learners — high volume, low retention unless onboarding is perfect.
  5. Enterprise developers — low volume, high retention, drive team adoption.

Read the full file on GitHub · 187 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 · 187 lines · 0 tokens per session scan A 337d5c004d36

Subscribe to this mod's changes

install-base is an agent published in the GitHub repository isaacsight/kernel (16 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,739 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.