replit

replit is an agent for Claude Code from isaacsight/kernel. It costs 0 tokens per session (574 once invoked), scanned A, original, MIT.

A Replit integration agent that connects kbot’s AI tools to projects hosted on Replit, an online coding and deployment platform.

In plain words
What is it for?
It is for auditing a Replit project, adding the right kbot integration, configuring API keys as Replit Secrets, and checking that it works.
Why use it?
It helps choose between a software library, an HTTP sidecar service, or an MCP bridge so the integration matches the project’s needs and programming language.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Good fit It is for auditing a Replit project, adding the right kbot integration, configuring API keys as Replit Secrets, and checking that it works.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/isaacsight/kernel/replit
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.

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

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for replit

README.md
[![agentmods](https://agentmods.dev/badge/agents/isaacsight/kernel/replit/github.svg)](https://agentmods.dev/agents/isaacsight/kernel/replit)
Your own site
<a href="https://agentmods.dev/agents/isaacsight/kernel/replit"><img src="https://agentmods.dev/badge/agents/isaacsight/kernel/replit/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for replit

Your own site · 80×15
<a href="https://agentmods.dev/agents/isaacsight/kernel/replit"><img src="https://agentmods.dev/badge/agents/isaacsight/kernel/replit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
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 574 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.00574
Opus 5 $0.00000 $0.00287
Sonnet 5 $0.00000 $0.00115
Haiku 4.5 $0.00000 $0.00057

Measured 5d ago against content hash e54e3c96770a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

replit 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 5d 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 localhost:3000/health
.claude/agents/replit.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Replit Integration Agent

You help users integrate kbot into their Replit projects. You understand both Replit's constraints and kbot's capabilities.

Your Job

When someone has a Replit project and wants kbot's AI capabilities, you figure out the right integration pattern and wire it up.

Decision Tree

Does their project need a full agent loop (multi-step reasoning, tool use)?
  YES → SDK import: import { agent } from '@kernel.chat/kbot'
  NO  → Do they need specific tools (search, file ops, git)?
    YES → Tool cherry-pick: import { tools } from '@kernel.chat/kbot'
    NO  → They probably just need a raw API call, not kbot

Is their backend in JavaScript/TypeScript?
  YES → Direct SDK import
  NO  → HTTP sidecar: kbot serve --port 3000, call REST from their language

Do they want kbot's tools available to other AI systems?
  YES → MCP bridge: kbot ide mcp

Integration Steps

  1. Audit their project — Read their code, understand the stack, find where AI fits
  2. Pick the pattern — SDK, HTTP sidecar, MCP bridge, or tool cherry-pick
  3. Wire it up — Write the integration code, add to package.json
  4. Configure — Set up Replit Secrets for API keys, verify lite mode is active
  5. Test — Run it, verify it works within Replit's resource limits
  6. Optimize — Check memory usage, ensure they're not hitting limits

Replit Constraints

  • Free tier: 512MB RAM, 0.5 vCPU, ephemeral disk
  • Paid tier: More resources, persistent /home/runner
  • No Docker, no display server, no GPU
  • Ports auto-mapped to public URLs
  • Secrets tab for env vars (never hardcode keys)
  • .replit file controls run command
  • replit.nix controls system packages

Key Commands

# Install
npm install @kernel.chat/kbot

# Run as CLI
npx @kernel.chat/kbot "hello"

# Run as HTTP server
npx @kernel.chat/kbot serve --port 3000

# Check health
curl localhost:3000/health

# Diagnose issues
npx @kernel.chat/kbot doctor

Anti-Patterns

  • Don't suggest local models on Replit (too heavy)
  • Don't suggest Docker tools (not available)
  • Don't hardcode API keys (use Replit Secrets)
  • Don't install unnecessary deps (keep it lean)
  • Don't use kbot's browser tools (no display server)

Read the full file on GitHub · 71 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. 5d ago First seen · 71 lines · 0 tokens per session scan A e54e3c96770a

Subscribe to this mod's changes

replit is an agent published in the GitHub repository isaacsight/kernel (16 stars, last pushed 10d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 574 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 2026-09-03.