Tools

Below is the complete list of 23 built-in tools the Kodik agent can use. Availability depends on the current mode and that mode’s switch in Harness settings. Harness lists only tools structurally offered in the selected mode and summarizes the rest as not offered. File access is governed by .kodikignore rules.

Tool reference

Tool	Purpose	Notes
read_file	Read file contents	Supports line ranges via the ranges parameter. Files larger than the model’s context window cannot be read directly. Respects .kodikignore.
edit_file	Edit one file	Modifies one existing file with one or more exact search/replace edits. Read the file first; multi-file work uses one serialized call per file. Checks linter diagnostics after editing.
create_file	Create one file	Creates one new file with complete contents and refuses to overwrite an existing path. Multi-file creation uses one serialized call per file.
delete_file	Delete one file	Deletes one existing file. Multi-file deletion uses one serialized call per file.
edit_notebook	Edit a Jupyter notebook	Supports insert, edit, delete operations on code and markdown cells. Languages: Python, JS, TS, R, Julia, SQL. Edited notebooks follow the file-change display setting; open notebook editors are refreshed and saved after tool edits, and dirty notebooks must be saved or discarded first.
shell	Run a terminal command	The block_until_ms: 0 parameter launches the command in the background and immediately returns a terminal_id for polling via command_status. A backgrounded command runs in its own terminal, so it never blocks later commands.
command_status	Poll a background process	Takes the terminal_id returned by shell. Used to retrieve incremental output from dev servers, watchers, and other long-running processes.
kill_terminal	Stop a background process	Takes the terminal_id returned by shell. Terminates a backgrounded command and frees its terminal — used to clean up or restart a dev server or watcher. Auto-approved.
glob	Find files by pattern	Supports patterns like **/*.ts.
rg	Full-text search (ripgrep)	Regex search with ripgrep options. Respects .kodikignore.
codebase_search	Semantic search over the codebase	Uses the local index — see Indexing.
read_lints	Read linter diagnostics	Returns errors and warnings from VS Code for one or more files (or the whole workspace).
web_fetch	Fetch URL contents	HTTPS only (plain HTTP allowed only for localhost). Returns the page as Markdown. 30-second timeout.
web_search	Search the web	Kodik provider only. Returns ranked results (title, URL, snippet) and usually a synthesized answer. Billed per search from your credit balance.
browser	Drive the integrated browser	Available in modes where the mode policy allows it when the browser tool is enabled in Harness. Opens pages, can reuse open browser tabs, launch a dev server, take screenshots, read and clear bounded console output, inspect, resize, navigate, and interact with the page.
todo_write	Manage a task list	Creates and updates task items for multi-step sessions.
memory	Save notes to memory	Writes notes to workspace/global memory or to session memory for the current task. See Memory.
sub_agent	Delegate a subtask to a subagent	Launches a child agent with its own context. With background: true it returns immediately and the child reports back when it settles. See Subagents.
agent_status	Check on a background subagent	Takes the agent_id from a background sub_agent launch. Reports status, goal, and elapsed time; wait: true blocks until the child settles and returns its full report. See Subagents.
ask_questions	Ask clarifying questions	Asks concise questions when ambiguity would change the implementation.
check_understanding	Check understanding	Runs a short comprehension check in Educator mode.
create_lesson	Create lessons	Builds an interactive HTML lesson and opens it in the Integrated Browser in Educator mode.
generate_plan	Generate plans	Produces a reviewable implementation plan in Plan mode.
MCP tools	Any tools from MCP servers	Depend on connected servers. See MCP.

Connected MCP tools are appended to the same Harness tool list. Their selected-mode switches affect the next turn; MCP Settings continues to own server and tool configuration. Harness includes only active MCP tools in prompt guidance and totals.

Details

read_file

The ranges parameter accepts an array of {start_line, end_line} objects and lets you read only the sections you need from a large file. If the file exceeds the size limit (derived from the model’s context window), read_file returns an informational message recommending rg or ranges instead.

read_file("src/server.ts", ranges=[{start_line: 1, end_line: 50}])

shell and command_status

For long-running processes (dev servers, watchers, log streams), launch with block_until_ms: 0 — it returns a terminal_id immediately. Use command_status with that ID to poll for new output without restarting the process.

Kodik runs these commands in the real integrated terminal. Shell integration is the terminal’s command-tracking protocol: when the selected shell supports it, Kodik receives exact command boundaries and exit codes. If integration is unavailable, Kodik still runs and captures the command, but reports Completion Unverified instead of inventing success or failure. Results stay scoped to the command that produced them; when a background process exits during an active turn, the model receives its real exit code when available and its final output.

A background process keeps its terminal busy. Later shell calls open another integrated terminal, so npm run dev can keep running while commands such as ls, tests, or HTTP checks execute alongside it. Finished terminals are reused for later sequential commands.

# Start a dev server in the background
terminal_id = shell("npm run dev", block_until_ms=0)

# Retrieve logs
command_status(terminal_id=terminal_id)

codebase_search

Uses a vector index that is built automatically. Search is meaning-based rather than keyword-based. Requires the index to exist — see Indexing.

web_fetch

Opens a headless browser, loads the page, and returns its content as Markdown. Output is truncated at 60 KB. Plain HTTP is blocked except for localhost.

web_search

Lets the agent discover current information it doesn’t have a link for: latest library versions and APIs, unfamiliar error messages, breaking changes, official documentation pages. Searches run server-side through the Kodik backend, so no search-provider API keys live on your machine, and each successful search is billed as a flat amount against the same credit balance as model usage — failed searches are never charged. The agent composes the two web tools: search to discover, then web_fetch the most promising result to read it in full.

Available only on the Kodik provider. On Ollama and custom/bring-your-own-key providers the tool is not offered, since searches there can’t be served or billed. Approval has its own auto-approve toggle (webSearch) — see Auto-Approve.

browser

Drives the same Integrated Browser surface you see in Kodik. The agent can start a preview at a URL, optionally run a dev-server command first and wait for the URL to respond, then stop the preview and the server it started.

Use browser for browser-rendered work. It can list existing browser tabs and focus the tab you are viewing, take screenshots, read and clear the bounded console buffer, resize to mobile/tablet/desktop breakpoints, navigate/reload/back/forward, inspect an element’s HTML/styles/box, read an accessibility snapshot, click/type/hover/drag, and evaluate page expressions when higher-level actions are not enough.

Opening arbitrary URLs, launching dev servers, interacting with pages, and running page scripts follow your auto-approval settings. Screenshots captured by the agent appear inline in the chat; click a screenshot thumbnail to open the full image in an editor tab.

.kodikignore

Tools including read_file, rg, and shell check .kodikignore before accessing files. Files matching patterns in .kodikignore are not accessible to the agent. See Ignore files.