# Agentic Tool Integration

Wiring a new tool the AI agent can call (not the recon pipeline): the tool registry...

- Repository: https://github.com/samugit83/redamon (3261 stars)
- Category: AI and agents
- License: MIT
- Last updated: 2026-11-01
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add samugit83/redamon --skill agentic-tool-integration -g -a claude-code -y`
Codex: `npx skills add samugit83/redamon --skill agentic-tool-integration -g -a codex -y`
Cursor: `npx skills add samugit83/redamon --skill agentic-tool-integration -g -a cursor -y`
Gemini CLI: `npx skills add samugit83/redamon --skill agentic-tool-integration -g -a gemini-cli -y`

## Description

Wiring a new tool the AI agent can call (not the recon pipeline): the tool registry, the phase map, the hardcoded dispatch chokepoint, and the duplicated execution paths that make a tool work in single mode but silently break in parallel plans. Trigger: adding or editing a tool the agent invokes; editing agentic/prompts/tool_registry.py, PhaseAwareToolExecutor in agentic/tools.py, agentic/orchestrator_helpers/nodes/execute_tool_node.py or execute_plan_node.py, TOOL_PHASE_MAP / DANGEROUS_TOOLS in agentic/project_settings.py, or a new MCP server in mcp/servers/.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

## When to Use

- Adding any tool the agent uses during a chat session (CLI wrapper, MCP tool, or API tool).

For a recon-pipeline tool (runs during a scan, writes the graph), use
`recon-tool-integration` instead. For the
per-setting/default multi-layer wiring, use
`project-settings-cascade`. For a whole
new attack *skill* (not a tool), use `builtin-agent-skill`.

---

## Critical Rules

The rest: https://github.com/samugit83/redamon/blob/HEAD/skills/agentic-tool-integration/SKILL.md