Agent Verification

AI agents can generate code, but still struggle to understand what they build. Reticle brings Jev-style machine-native runtime perception to web & desktop applications.

📚 Two books on harness engineering — the design philosophies behind Claude Code & Codex: constraints, query loops, context governance, multi-agent verification. harness-books.agentway.dev

Subagent Verification for Claude AI Code Networks 2026

Iterative, graph-based autonomous research agent with reflection, web search verification, and structured report compilation.

Autonomous coding agent MCP server that navigates codebases, performs intelligent semantic refactoring, and executes build verification.

IronBee CLI - Verification and Intelligence Layer for Agentic Development

Independent security verification for code written by humans and AI agents. Scan, repair, then prove it — Dvalin runs your project's own checks and issues a Verified Fix Record anyone can re-derive offline. Local-first, policy-bound, MIT.

Self-evolving second brain with 35 AI skills, 10 agents, and people CRM. Closed-loop harness: a V-model verification lifecycle where the worker never grades its own homework. Plus paired anti-slop design skills for marketing and product UI. Works with Claude Code, Cursor, Kiro, Gemini CLI, Codex.

SEO AGI -- The first AI agent that writes pages Google ranks AND LLMs cite. One command in, ranking page out. Built on DeerFlow, powered by 2026 SEO + GEO strategies tested / working. Forensic competitive analysis, 500-token chunk architecture, entity consensus, verification tags. BYOK for GSC, Ahrefs, SEMRush. Works w/ OpenClaw, Claude Code, Codex

AGI-oriented, hallucination-resistant AI coding runtime grounded in evidence, tools, memory, agents, and verification.

Give your AI agent a phone number: order a private number in 200+ countries over the API, read the SMS verification code, hand the number back. The widest country coverage in the category, checkable with one API call.

On Page Agent -- The first AI agent that writes pages Google ranks AND LLMs cite. One command in, ranking page out. Built on DeerFlow, powered by 2026 SEO + GEO strategies tested / working. Forensic competitive analysis, 500-token chunk architecture, entity consensus, verification tags. BYOK GSC, DataforSEO. Works w/ OpenClaw, Claude Code, Codex

AI-powered GA4 + GTM event tracking — automates site analysis, event schema, GTM sync, preview verification, and publishing. Works with Cursor, Codex, and any AI agent.

Deletion-first Agent Skill for removing test bloat, verification theater, and speculative fallbacks while preserving behavior.

Fast, interruptible verification browser for AI coding agents: 35 ms checks, pixel diffs, live human hand-off

Deepdive skill for Claude Code — 12-phase research pipeline: plan-review gate, parallel sub-agent search, claims-ledger triangulation with dissent protection, relevance × authority evidence filter, multi-angle red team, four-layer citation verification. 105 blocks, 29 channels, 460+ stat sources, 47 APIs, 1072 verified endpoints.

Claude Code plugin for Elixir/Phoenix/LiveView — 26 specialist agents, Iron Laws enforcement, and Tidewave MCP integration. Plan features with parallel research agents, execute with automatic verification, review with 4-agent parallel audits, and capture learnings as reusable knowledge.

Agent skill that conducts an interactive architectural walkthrough and verification quiz over a codebase.

Continuous, model-version-bound verification of agent skills: run a skill's eval suite with and without the skill, emit hash-verified dated receipts with confidence bands, and diff them into drift reports.

Repository retrieval and context engine for Claude Code and Codex: finds relevant code, reuses project knowledge, and pairs each task with specialist skills and verification.

A universal, industry-neutral taxonomy of cognitive core skills (perception, memory, reasoning, planning, action, verification, learning, governance) for LLMs, SLMs, AI agents, and world models — with schemas, 159 skill cards, benchmarks, and CI.

Agent skills that fact-check the internet: claim-by-claim verification with sources and a 0-10 BS score for any YouTube video, article, tweet, or PDF

Portable CC-inspired skills for memory, verification, multi-agent coordination, context compression, and proactive coding-agent workflows.

Video understanding and self-verification for AI agents. Turn videos, streams, and agent screen recordings into searchable, timestamped evidence—then use THE LOOP to inspect, fix, and verify the work. MCP, CLI, REST, local-first.