Built in Tools

Built-in Tools

CortexPrism ships with 43 built-in tools available to all agents. Tools are registered in src/tools/registry.ts via registerAllBuiltins() and gated through the security policy validator before execution.

File System Tools

Tool	Description
file_read	Read file contents; auto-extracts PDF text; language detection for 40+ languages
file_read_enhanced	Enhanced reader with language detection, binary detection, large file warnings
file_write	Write or overwrite a file
file_edit	Exact string replacements in files
file_patch	Apply unified diff patches
file_delete	Delete a file or directory
file_rename	Rename or move a file
file_copy	Copy files or directories with overwrite protection
file_move	Move files/directories with overwrite protection
file_list	List directory contents with type markers
file_tree	Recursive tree view of directories
file_info	File/directory metadata (size, type, timestamps)
file_search	Regex search across file contents
file_glob	Find files matching glob patterns
file_diff	Compare two files with unified diff format
file_undo	Undo the last file change
file_redo	Redo a previously undone change

All file tools support workspace: "agent"/"global" parameter for scoped operations. File edits are auto-committed to git with undo/redo support.

Shell

Tool	Description
shell	Execute local shell commands — gated by policy validator and optional human approval

Safety: Default deny rules block rm -rf /, fork bombs, direct disk writes, chmod 777 /.

Web Tools

Tool	Description
web_search	Web search via DuckDuckGo
web_search_enhanced	Multi-provider search with intelligent fallback (Brave → Tavily → DuckDuckGo)
web_fetch	Fetch URL content as cleaned plain text (strips HTML, scripts, styles)
web_fetch_enhanced	Enhanced fetch with HTML-to-Markdown, retry with exponential backoff
brave_search	Web search via Brave Search API
tavily_search	Web search via Tavily API
serpapi_search	Web search via SerpAPI
firecrawl	Web scraping via Firecrawl
docs_search	Official library documentation search via Context7 (25+ libraries, 24h caching)

Code Execution

Tool	Description
code_exec	Run code in isolated Docker/gVisor containers with resource limits

Supports Python, JavaScript, TypeScript, Bash, Ruby, Go, Rust. Network disabled by default. Auto-fix loop: LLM receives error feedback and retries (up to 4 rounds).

Browser Automation

Tool	Description
browser	Headless Playwright-powered browser automation — navigate, click, type, screenshot, snapshot, evaluate, wait

Configurable timeout (30s). Actions gated through security supervisor for sensitive operations. Base64 PNG screenshot output and accessibility snapshots.

GitHub Tools

Tool	Description
git_push	Stage, commit, and push to remote
github_pr_create	Create a pull request
github_pr_list	List pull requests
github_issue_create	Create an issue
github_issue_list	List issues

Code Intelligence Tools

Tool	Description
code_index	Full repository indexing with incremental sync and file change detection
code_search_symbol	FTS5-backed symbol search across projects
code_trace_path	Bidirectional call graph traversal with depth limits and hotspot analysis
code_get_architecture	System architecture diagram extraction (layers, modules, dependencies)
code_analyze_impact	Blast radius analysis (callers, callees, dead code detection, complexity)
code_list_projects	Project registry with language stats and node/edge counts

Uses tree-sitter WASM parser for 14+ languages. Full-text search via FTS5 on code_nodes.

Computer Use (GUI Automation)

Tool	Description
computer	GUI automation — screenshot, click, type, key, scroll, mouse_move, drag, and 15+ actions

Requires xvfb, xdotool, scrot on Linux. All actions gated through policy validator; sensitive data auto-blocked.

Agent & Sub-Agent Tools

Tool	Description
sub_agent	Spawn a typed child agent (explorer, coder, researcher, planner, generalist)
node_dispatch	Dispatch tasks to remote distributed nodes

Memory Tools

Tool	Description
memory_note	Persist notes to episodic memory
memory_search	Search across episodic, semantic, reflection, and graph memory with hybrid (keyword + vector) search

Data & Utility Tools

Tool	Description
db_query	Read-only database querying across cortex/memory/lens/plugins/session databases
json_query	JSONPath-like expression support ($.property, $.array[0], $.array[*], $.**)
regex_utils	Regular expression utilities — match, replace, test, split, exec
env_manager	Environment variable management with whitelist-based set security
code_snippet	Code block extraction from markdown with line numbers and language detection
structured_extract	LLM-powered entity/relationship extraction with JSON-Schema validation
image_analyze	Multimodal image analysis via 18+ LLM providers
schedule	Cron-based job scheduling with full lifecycle (create/list/cancel/status/due)

Skill Tools

Tool	Description
load_skill	Load a skill by name (auto-records usage for quality tracking)
skill_read	Read/List skills with lifecycle and origin filtering
skill_write	Create/update/delete/merge/promote/deprecate skills with 8 operations

Voice Tools

Tool	Description
speak	Text-to-speech via configured TTS provider
listen	Speech-to-text via configured STT provider

Dashboard Tools

Tool	Description
dashboard_manage	CRUD operations on dashboard widgets (list, add, remove, update)

Tool Interface

Every tool implements:

interface Tool {
  definition: ToolDefinition;
  execute(args: Record<string, unknown>, ctx: ToolContext): Promise<ToolCallResult>;
}

interface ToolDefinition {
  name: string;
  description: string;
  params: ToolParam[];
  capabilities: ToolCapability[];
}

Security & Policy Validation

Every tool call passes through the security system before execution:

Agent → Tool Intent → Policy Validator → (Sensitive Data?) → LLM Supervisor → Human Approval → Executor

• Policy validator — regex allow/deny rules evaluated against every shell command, file path, and network request
• LLM supervisor — sensitive data access (memory_search, db_query, browser screenshots) requires approval from a fast LLM with decision caching and human escalation
• Human approval — CLI prompts and Web UI modal for uncertain/unapproved access requests

See Also

• Security — Parallax policy validator and LLM supervisor
• Security Supervisor — 3-layer access control architecture
• Agent Loop — How tools integrate into the agent lifecycle
• Plugin System — Adding custom tools via plugins
• Adding a Tool — Step-by-step guide for new tools