Tools Reference

50+ built-in tools across 8 categories for autonomous coding operations. File operations, git, shell, web search, testing, memory, MCP, and more.

XibeCode provides 50+ built-in tools across 8 categories for autonomous coding operations. These tools are automatically available to the AI agent based on the current mode's permissions.

Tool Categories Overview

Category	Tools	Description
File Operations	8	Read, write, edit, delete files
Directory Operations	3	List, search, create, move
Git Operations	7	Status, diff, checkpoints, revert
Shell & Code Search	2	Execute commands, grep code
Web Operations	2	Search, fetch URLs
Test Operations	4	Run tests, generate tests, analyze code
Memory Operations	6+	curated_memory, session_search, skills, lessons
Browser Operations	8	Screenshots, testing, performance, accessibility

Reliability Controls (v0.9.1)

Recent versions add stronger guardrails around tool execution quality:

Evidence-aware completion gating: the agent must gather grounded evidence before it can conclude work.
Post-edit verification: edit/write actions are validated with read-back checks.
Improved loop resistance: repeated same/near-same tool input patterns are detected and blocked earlier.
Safer memory recall: recalled memories are treated as hints and filtered by relevance.
Grounded context compaction: old context keeps summarized facts instead of silently dropping all detail.

File Operations

read_file

Read the contents of a file.

{ "path": "src/app.ts", "start_line": 1, "end_line": 100 }

read_multiple_files

Read multiple files at once for context.

{ "paths": ["src/app.ts", "src/utils.ts", "package.json"] }

write_file

Write content to a file (creates or overwrites).

{ "path": "src/new-file.ts", "content": "export const hello = 'world';" }

edit_file

Edit a file using search and replace.

{
  "path": "src/app.ts",
  "search": "const oldValue = 1;",
  "replace": "const newValue = 2;"
}

edit_lines

Edit specific line ranges in a file.

{
  "path": "src/app.ts",
  "start_line": 10,
  "end_line": 15,
  "content": "// New content"
}

insert_at_line

Insert content at a specific line.

{
  "path": "src/app.ts",
  "line": 5,
  "content": "import { newModule } from './module';"
}

verified_edit

Edit with verification — ensures the search pattern exists before replacing.

{
  "path": "src/app.ts",
  "search": "exact content to find",
  "replace": "replacement content"
}

delete_file

Delete a file.

{ "path": "src/deprecated.ts" }

Directory Operations

list_directory

{ "path": "src/", "recursive": false }

search_files

{ "pattern": "*.ts", "path": "src/" }

create_directory

{ "path": "src/new-feature/" }

move_file

{ "source": "src/old-name.ts", "destination": "src/new-name.ts" }

Git Operations

get_git_status

Returns staged, unstaged, and untracked files.

get_git_diff_summary

{ "staged": true }

get_git_changed_files

Get list of files changed in the current branch.

create_git_checkpoint

{ "message": "before auth refactor", "strategy": "stash" }

revert_to_git_checkpoint

{ "checkpoint_id": "stash@{0}" }

git_show_diff

{ "path": "src/app.ts" }

get_mcp_status

Get MCP server status.

Shell Commands

run_command

{
  "command": "npm install express",
  "cwd": "./",
  "timeout": 30000,
  "stdin": "input data"
}

Dangerous commands like rm -rf / are blocked automatically.

In cloud sandbox_full mode, file and command tools execute against the remote sandbox workspace (not your host absolute paths). Use repo-relative paths for reliable results.

Code Search

grep_code

{
  "pattern": "function.*async",
  "path": "src/",
  "include": "*.ts",
  "case_sensitive": false
}

Web Operations

web_search

{ "query": "typescript best practices 2024", "num_results": 5 }

fetch_url

{ "url": "https://api.example.com/data", "method": "GET" }

Test Operations

run_tests

{ "path": "src/", "filter": "auth", "verbose": true }

Supports: Vitest, Jest, Mocha, pytest, Go test, Cargo test.

get_test_status

Returns passed, failed, and skipped test counts.

Memory Operations

curated_memory

Durable global memory in ~/.xibecode/memories/MEMORY.md and USER.md. Prefer an atomic operations batch for multi-change or consolidation when full.

{
  "target": "memory",
  "operations": [
    { "action": "remove", "old_text": "stale fact" },
    { "action": "add", "content": "Prefer pnpm for all package installs" }
  ]
}

target: memory (agent notes) or user (profile/preferences)
Single-op fields: action, content, old_text
Frozen into the system prompt at session start; mid-session writes apply next session
On success: done=true — do not re-save the same entry

See Memory.

session_search

Search past sessions when details are not in MEMORY.md.

{ "query": "auth middleware fix", "limit": 8 }

save_skill / list_skills / view_skill

save_skill — write a reusable procedure under ~/.xibecode/skills/learned/
list_skills — progressive disclosure (metadata only)
view_skill — load full skill body by name

remember_lesson

{
  "trigger": "Build failed after git pull",
  "action": "Ran pnpm install and rebuilt",
  "outcome": "Typecheck passed",
  "tags": ["deps", "pnpm"]
}

update_memory

Legacy/project memory key-value style updates (project auto-memory layer). Prefer curated_memory for durable cross-session facts.

Browser & screenshots

Playwright is not bundled with the CLI (no Chromium download on install). Prefer:

take_screenshot (agent-browser first, then headless Chrome/Chromium)
run_command + agent-browser for interactive browser flows
MCP or project-local Playwright if you need full E2E in the consumer repo

Optional: install agent-browser globally on supported platforms. Override with XIBECODE_PREFERRED_BROWSER=chrome.

take_screenshot

{
  "url": "http://localhost:3000",
  "path": "screenshots/home.png",
  "fullPage": true
}

path must be under the project workspace (e.g. screenshots/home.png). Absolute /tmp/... paths are remapped into screenshots/.
Result includes a MEDIA:… line — put it in the final reply so Telegram uploads the PNG.
Localhost is allowed.

read_only: read_file, read_multiple_files, list_directory, search_files
write_fs: write_file, edit_file, edit_lines, insert_at_line, delete_file, move_file, create_directory
git_read: get_git_status, get_git_diff_summary, get_git_changed_files, git_show_diff
git_mutation: create_git_checkpoint, revert_to_git_checkpoint
shell_command: run_command
tests: run_tests, get_test_status
network: web_search, fetch_url
context: grep_code, get_context

Safety Features

Command Blocking — Dangerous commands like rm -rf / are blocked
Risk Assessment — High-risk operations are flagged with warnings
Automatic Backups — Files are backed up before editing
Dry-Run Mode — Preview changes without executing
Mode Permissions — Tools are restricted based on current mode
Completion Evidence Gate — Prevents premature “done” responses without grounded proof

Extending Tools

You can add custom tools via:

Plugins — JavaScript/TypeScript modules
MCP Servers — External tool servers

Next Steps

Agent Modes — Learn about mode permissions
Plugins — Create custom tools
Examples — See tools in action

On this page

How can I help?