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/kilo-org/kilocode/chat-interfacegit clone --depth 1 https://github.com/Kilo-Org/kilocodeWhat 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 | $0.00011 | $0.02152 |
| Opus 5 | $0.00005 | $0.01076 |
| Sonnet 5 | $0.00002 | $0.00430 |
| Haiku 4.5 | $0.00001 | $0.00215 |
Grade A, and why
chat-interface 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.
How it starts
The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chatting with Kilo Code
{% callout type="tip" %} Bottom line: Kilo Code is an AI coding assistant. You chat with it in plain English, and it writes, edits, and explains code for you. {% /callout %}
{% callout type="note" title="Prefer quick completions?" %} If you're typing code in the editor and want AI to finish your line or block, check out Autocomplete instead. Chat is best for larger tasks, explanations, and multi-file changes. {% /callout %}
Quick Setup
{% tabs %} {% tab label="VSCode" %}
Click the Kilo Code icon ({% kiloCodeIcon /%}) in VS Code's Primary Side Bar to open the sidebar chat. You can also pop it out into an editor tab for a larger workspace.
{% /tab %} {% tab label="CLI" %}
Open your terminal and run kilo to launch the interactive terminal interface (TUI). You'll see a prompt where you can start typing requests immediately. The TUI is fully keyboard-driven — no mouse required.
{% /tab %} {% /tabs %}
How to Talk to Kilo Code
The key insight: Just type what you want in normal English. No special commands needed.
{% image src="/docs/img/typing-your-requests/typing-your-requests.png" alt="Example of typing a request in Kilo Code" width="800" caption="Example of typing a request in Kilo Code" /%}
Good requests:
create a new file named utils.py and add a function called add that takes two numbers as arguments and returns their sumin the file @src/components/Button.tsx, change the color of the button to bluefind all instances of the variable oldValue in @/src/App.js and replace them with newValue
What makes requests work:
- Be specific - "Fix the bug in
calculateTotalthat returns incorrect results" beats "Fix the code" - Use @ mentions - Reference files and code directly with
@filename - One task at a time - Break complex work into manageable steps
- Include examples - Show the style or format you want
{% callout type="info" title="Chat vs Autocomplete" %} Use chat when you need to describe what you want, ask questions, or make changes across multiple files.
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.
- yesterday First seen · 189 lines · 11 tokens per session scan A c5706b028f3d
chat-interface is an agent published in the GitHub repository Kilo-Org/kilocode (27,081 stars, last pushed 2d ago), licensed MIT. It adds 11 tokens to every session and 2,152 once invoked, about $0.0001 per session on Opus 5. 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.
Other agents, from other repositories
Audit-Commits
Compares HEAD against a tag, identifies user-facing commits, ensures they have linked issues and CHANGELOG entries.
backseat-dev
Backseat Driver VS Code extension development — ClojureScript shadow-cljs, Ex action/effect framework, MCP socket server, Calva REPL integration, structural editing tools, Datascript output log, skill authoring, REPL-driven interactive programming. Use when: developing Backseat Driver features, debugging extension…
deep-review-orchestrator
Use this agent when the user asks to perform a comprehensive deep review using multiple competing AI models. Trigger phrases include: 'perform a deep review with multiple perspectives' 'get competing reviews of these changes' 'conduct a thorough review using different models' 'review these changes with multiple LLMs'…
inspector-driver
Drives the vscode-inspector MCP against a live VS Code + GitLens instance and returns raw evidence (probe values, console/log excerpts, geometry, measurements) as text. Default executor for live-inspection driving so the Opus orchestrator only reasons over distilled results. Returns evidence; does NOT judge, fix, or…
bd-tester
Agent for testing Backseat Driver tools.
bootstrap
Mission: Initialize and converge a governed, structured project context for GAAI.