LanNguyenSi

Agent Grounding — AI skill for Claude Code

AI community

Verification framework for AI agents: runtime checks, claim validation, hypothesis tracking.

How to install Agent Grounding

This entry records only its repository, not the path inside it, so there is no exact command to give. Open LanNguyenSi/agent-grounding and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Agent Grounding does

Verification framework for AI agents: runtime checks, claim validation, hypothesis tracking.

Alternatives in AI

Flow Deliver — Multi-AI validation, scoring, and review using Codex and Gemini CLIs (Double Diamond Deliver phase) 2.8k ★
Gtm Engineer Skills — Claude Code skill for improving website AEO (AI Engine Optimization) and GEO (Generative Engine Optimization) 761 ★
Cwc Long Running Agents — Claude Code's built-in /goal command gives you a generator/evaluator loop out of the box: set a completion con 668 ★

README

agent-grounding

**Verification and debugging framework for AI agents.**

Stop agents from acting on stale assumptions, making unsupported claims, or silently switching hypotheses mid-investigation. A workspace of TypeScript packages (understanding-gate, evidence ledger, claim gate, hypothesis tracker, runtime reality checker, debug playbook engine, readme-first resolver, domain router, grounding-wrapper, grounding-sdk, review-claim-gate, MCP server) that an agent harness wires into its session and tool-call lifecycle.

Most agent tooling helps a model *talk* about a problem. `agent-grounding` makes it *prove* what it has actually checked, what it has only assumed, and what it has ruled out, before the next destructive command runs.

Architecture

Agents reach the stack two ways: a **PreToolUse gate** that blocks destructive commands until claims are grounded, and **access surfaces** (MCP, SDK, CLI) over a shared evidence ledger.

flowchart LR
    subgraph clients["Agent harness / MCP clients"]
        direction TB
        cc["Claude Code"]
        oc["OpenCode"]
        hn["harness"]
    end

    subgraph gate["Pre-execution gate · PreToolUse"]
        direction TB
        ug["understanding-gate
report approved before destructive tools"]
        rrc["runtime-reality-checker
blocks compose / systemctl / kill on drift"]
    end

    subgraph core["Verification core"]
        direction TB
        cg["claim-gate"]
        ht["hypothesis-tracker"]
        helpers["grounding-wrapper · domain-router
readme-first-resolver
debug-playbook-engine · review-claim-gate"]
        el[("evidence-ledger
~/.evidence-ledger/ledger.db")]
    end

    subgraph surfaces["Access surfaces"]
        direction TB
        mcp["grounding-mcp · JSON-RPC
ledger_add · ledger_summary · claim_evaluate"]
        sdk["grounding-sdk
verify / track / validate"]
        cli["evidence-ledger CLI"]
    end

    clients --> gate
    clients --> surfaces
    gat