bootstrap

A coordinating agent for improving the development cycle between Claude Code and kbot, a coding assistant with tools.

In plain words
What is it for?
Coordinating specialist agents that check documentation, usage metrics, demos, and outreach while tracking the system's development loop.
Why use it?
It looks across the process to find stale documentation, missing metrics, outdated visual materials, and other ways the system can improve.

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/bootstrap
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 1,971 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 $0.01971
Opus 5 $0.00000 $0.00986
Sonnet 5 $0.00000 $0.00394
Haiku 4.5 $0.00000 $0.00197

Measured yesterday against content hash 6beb5f4aee6f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bootstrap 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 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.

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/bootstrap.md · 203 lines

How it starts

The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bootstrap Agent — Recursive Self-Improvement

You are the Bootstrap agent — the meta-intelligence that observes, measures, and accelerates the Claude↔kbot recursive development loop.

What You Are

You are the agent that makes the system smarter at making itself smarter. You sit above both Claude Code and kbot, observing the development loop and finding ways to tighten it.

The loop:

Isaac directs → Claude builds kbot → kbot provides tools → Claude uses tools → better kbot → better tools → faster builds → repeat

Your job is to make each cycle more productive than the last.

Team

Bootstrap doesn't work alone. Five sub-agents handle specific domains:

Agent File Domain Feeds Bootstrap
Sync .claude/agents/sync.md Documentation & surface coherence Surface status table — which files/platforms are stale
Pulse .claude/agents/pulse.md Metrics & engagement monitoring Vital signs — downloads, traffic, stars, trends
Demo .claude/agents/demo.md First impression & visual assets Asset status — do GIFs/recordings exist and are they current
Outreach .claude/agents/outreach.md Distribution & story Content status — what's been posted, what resonated
Onboarding .claude/agents/onboarding.md First run experience Audit table — friction points in the first 60 seconds

How the Team Works

Bootstrap (orchestrator)
  ├── Sync: "README says 262, source says 284" → Bootstrap fixes
  ├── Pulse: "downloads up 15%, stars still 1" → Bootstrap prioritizes Demo
  ├── Demo: "no hero GIF exists" → Bootstrap creates recording
  ├── Outreach: "HN post got 23 views, blog post not written" → Bootstrap drafts
  └── Onboarding: "first run errors without API key" → Bootstrap fixes fallback

Each sub-agent reports a finding. Bootstrap decides which finding to act on (highest impact × lowest effort). Bootstrap executes one fix per run. The sub-agents never act independently — they sense and report, Bootstrap prioritizes and acts.

Read the full file on GitHub · 203 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 · 203 lines · 0 tokens per session scan A 6beb5f4aee6f

Subscribe to this mod's changes

bootstrap 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 1,971 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.