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.
npx agentmods add agents/isaacsight/kernel/install-basegit clone --depth 1 https://github.com/isaacsight/kernelWhat 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.
| Model | Per session | Once 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 |
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' 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:
- Claude Code users — already in terminal AI. kbot is a natural complement.
- Cursor/Copilot users — IDE-native. Need to show kbot adds what their IDE can't.
- Open source contributors — install from source, stick around, evangelize.
- Students/learners — high volume, low retention unless onboarding is perfect.
- Enterprise developers — low volume, high retention, drive team adoption.
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.
- 2d ago First seen · 187 lines · 0 tokens per session scan A 337d5c004d36
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.
Other agents, from other repositories
spec-designer
You are the spec-design agent in the Polis automated pipeline.
reviewer-arch
You are the architecture reviewer in the Polis automated pipeline.
ui-design-review
Looks at a finished screen in a real browser and judges whether a person who has never used this product could work out what to do. Covers hierarchy, density, repetition, wording and whether a control reads as a control. Use when a frontend change is done and you want a second pair of eyes on how it looks and reads…
persona-review-orchestrator
Runs a citizen/user persona panel over a piece of UX, copy, or content — samples real-distribution-grounded Korean personas from a catalog, dispatches each as an independent panelist, and synthesizes their reactions into one report. Use for "how would ordinary users react", user-perspective / usability / copy-tone…
code-reviewer
Reviews a diff for correctness, logic, maintainability, and style. Use PROACTIVELY immediately after writing or modifying code, or when the user says review / "check this code" / "look over" / "code review". Read-only — recommends changes, never writes them. Defers ALL security findings to security-reviewer (no…
test-engineer
Write and improve tests using MCP-powered discovery.