kilo

A coding agent that connects to more than 500 language models through the models.dev catalogue and communicates through ACP, a standard way for coding tools to control an agent.

In plain words
What is it for?
Use it to ask an agent to explain a codebase, authenticate with a provider, list available models and run sessions through the Kilo command-line tool or an agents-wire integration.
Why use it?
It lets developers use one coding-agent interface while choosing models from different providers. It also provides installation, login and model-selection instructions.

Agent

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/pivanov/agents-wire/kilo
Clone the repo
git clone --depth 1 https://github.com/pivanov/agents-wire
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 616 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 $0.00616
Opus 5 $0.00000 $0.00308
Sonnet 5 $0.00000 $0.00123
Haiku 4.5 $0.00000 $0.00062

Measured yesterday against content hash 8f0b6f7a7a90, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

kilo 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.

apps/docs/agents/kilo.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kilo

Agent ID: kilo

Kilo is a coding agent that proxies 500+ models via models.dev. Speaks ACP natively via kilo acp.

Install

npm install -g @kilocode/cli
kilo auth login --provider <id>
# or: export KILO_API_KEY="your-api-key"

See kilocode.ai for supported providers and setup instructions.

Quick Start

import { agents } from "@pivanov/agents-wire";

const result = await agents.ask(
  "kilo",
  "Explain this codebase",
  {
    permission: "auto-allow",
  },
);

console.log(result.text);

Model Selection

Kilo proxies 500+ models via models.dev. Use listAvailableModels() to get the live list (calls kilo models under the hood):

import { definitionFor } from "@pivanov/agents-wire/catalog";

const def = definitionFor("kilo");
const models = (await def.listAvailableModels?.()) ?? def.models ?? [];

// models is IAgentModelOption[] - provider/model pairs from models.dev
console.log(models.map((m) => m.id));
// e.g. ["anthropic/claude-sonnet-4-7", "openai/gpt-5", ...]

The static catalog shows a "Default" placeholder before kilo models can be called. options.model is sent via ACP setSessionConfigOption (best-effort). Effort kind varies per upstream model - check IAgentModelOption.effort on each entry.

Capabilities

Feature Supported
ask / stream / session
askJson
MCP stdio
MCP http/sse
Session listing (listSessions)
Tool call interception

Cost Tracking

Cost reporting depends on the upstream model and provider. Token-priced models report per-turn costUsd. Check result.cost and session.cost.snapshot.totalUsd to see what is available for your configured provider.

Auth Failure Detection

If KILO_API_KEY is missing or kilo auth login has not been run, the SDK catches the authentication-failure pattern in stderr and throws AgentUnauthenticatedError.

Gotchas

Read the full file on GitHub · 81 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 · 81 lines · 0 tokens per session scan A 8f0b6f7a7a90

Subscribe to this mod's changes

kilo is an agent published in the GitHub repository pivanov/agents-wire (5 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 616 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 2026-08-31.

Related

Other agents, from other repositories

codex-execute

Implement a SPECIFIC, well-defined plan or plan-step with Codex. Use ONLY when the user has a written plan, plan-step, named files, or acceptance criteria to execute ("execute this via codex", "implement this plan", "/codex:execute", or a --plan file is in context). Do NOT use when the user is stuck/exploring (use…

greenpolo/cc-multi-cli-plugin · 98 tokens

cursor-delegate

Delegate a SPECIFIC, well-defined implementation task or plan step to Cursor in agent mode on the Auto model. Cursor is the fast lane for mechanical writing — long file writes (200+ lines), pattern-following across many files, bulk refactors. Supports autonomous multi-step runs via --until-done. Pair with…

greenpolo/cc-multi-cli-plugin · 84 tokens

cursor-research

Delegate read-only EXTERNAL web/documentation research to Cursor. Use when the user wants current library/API/docs research, "what's the current way to…", or to compare approaches — and you'd rather not spend Claude's context on web reading. Cursor runs read-only (ask mode) with web search + fetch and returns findings…

greenpolo/cc-multi-cli-plugin · 92 tokens

opencode-research

Delegate read-only EXTERNAL web/documentation research to OpenCode. Use when the user wants current library/API/docs research, "what's the current way to…", or to compare approaches — and you'd rather not spend Claude's context on web reading. OpenCode runs read-only (ask mode) with web search + fetch and returns…

greenpolo/cc-multi-cli-plugin · 97 tokens

codex-rescue

Hand an OPEN-ENDED or stuck problem to Codex for independent investigation. Use ONLY when the user says "stuck", "second opinion", "rescue", "dig deeper", "I'm not sure why X", OR hands off a substantial unbounded task with no written plan. Do NOT use when a plan or plan-step file is in context (use codex-execute) or…

greenpolo/cc-multi-cli-plugin · 99 tokens

cursor-explore

Delegate quick read-only CODEBASE exploration to Cursor. Use to answer questions about the current repository ("where is X handled?", "how does Y flow?", "summarize the adapter layer") without spending Claude's tokens reading files. Cursor runs read-only (ask mode) using semantic search, grep, and its Explore…

greenpolo/cc-multi-cli-plugin · 90 tokens