AI Guard Coding Agents — AI skill for Claude Code
A CLI that runs AI coding agent actions through Datadog AI Guard before they are executed.
How to install AI Guard Coding Agents
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open DataDog/ai-guard-coding-agents and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What AI Guard Coding Agents does
A CLI that runs AI coding agent actions through Datadog AI Guard before they are executed.
Alternatives in AI
- Peekaboo — Peekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, o 3.2k ★
- Browserwing — BrowserWing turns your browser actions into MCP commands Or Claude Skill, allowing AI agents to control browse 1.2k ★
- Kibitz — Real-time decoded feed of AI agent actions — monitor multiple Claude Code & Codex sessions, see exactly what e 521 ★
README
AI Guard for Coding Agents
  
[!IMPORTANT] **Experimental.** This is an early experiment to validate our approach to securing coding agents; not a production-ready product, and not meant for dogfooding at scale. The deployment method here does not reflect the final product, which will use a more secure approach with full data-privacy guarantees. **Do not use this project in data-sensitive coding sessions**.
A CLI that runs AI coding agent actions through [Datadog AI Guard](https://docs.datadoghq.com/security/ai_guard/) before they are executed.
When a coding agent reads a file, runs a command, or loads a skill or plugin, that content can carry malicious intent: prompt-injection payloads, instructions to exfiltrate secrets, attempts to install hostile tools, and similar. This CLI hooks into the agent's lifecycle, evaluates each tool call against AI Guard, and denies the operation when policy is violated.
Denied tool calls provide a useful remediation to the user so they can clearly see what steps are required to fix the issue. Setting `DD_AI_GUARD_BLOCK=false` switches to observe-only: evaluations are still emitted, but no decision is enforced. Every evaluation (allow or deny) is emitted to Datadog with the session, tool, model, and risk category attached.
Installation
A single command bootstraps the CLI on Linux and macOS — it downloads the latest signed binary, verifies its SHA-256 checksum and [Sigstore build-provenance signature](#ver
Related Skills
Aigate AI Git Workflow Guard CLI
Pre-push Git safety CLI for AI-assisted coding: catch risky changes, possible secrets, weak PR readiness, and
Auto Guard
A cached auto command review guard for AI coding agents — rules, memory and LLM verdicts (allow/deny/ask) befo
Code Agent
An AI Agent that operates on GitHub Actions. By using this action, you can directly invoke Coding Agent CLI fr
Notchd
A flight recorder and undo button for every AI coding agent on your Mac. Records every file and command across
Slb
Two-person rule CLI for AI coding agents: peer review and approval required before running potentially destruc
Wheel Hub
Stop reinventing the wheel. MCP server + CLI that makes AI coding agents search GitHub for existing open-sourc
Related Agents
Audit Logs
Query and manage Datadog Audit Trail events for compliance, security auditing, and tracking user actions acros
Codex Analyst
Token-heavy READ-ONLY analysis, codebase surveys, audits and inventories, executed by the Codex CLI rather tha
Spendly Test Runner
Use this agent when pytest tests for a Spendly feature have already been written and need to be executed and a
