Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    consensus verification

    1

    Verify product consensus by analyzing multiple search streams for affiliate bias and manufactured SEO signals.

    $10

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    consensus verification

    consensus verification

    Example session with this skill installed

    /consensus-verification mesh wifi for a 3,000 sq ft house under $400

    • Read your context and instructions
    • Compiled the consensus verification

    I have initialized a new consensus check for mesh wifi systems. The criteria are locked and the initial search across four streams (Brave, Ceramic, Exa, Linkup) is complete.

    Mesh WiFi (3,000 sq ft, <$400) — Consensus Check (2024-05-20)

    Verdict: Partly manufactured — High agreement on the top pick is driven by identical affiliate link structures across 60% of surfaced domains.

    candidaterange weight (0.4)throughput (0.3)value (0.3)weighted scoreevidence (source class)
    TP-Link Deco XE750.90.850.950.90Independent Testing
    Eero 6+ (3-pack)0.70.600.800.70Affiliate/Editorial
    ASUS ZenWiFi XT80.850.900.600.79User-generated/Testing

    Bias findings

    Monetization: 8 of the top 10 results for the "problem-framed" query contained Amazon Associate IDs with missing or buried disclosures.

    Manufactured agreement: Three domains (TechRadar clones) shared identical "Pros/Cons" copy for the Eero 6+, suggesting a shared content syndication source.

    Adversarial: Found hidden "Ignore previous instructions" text in the footer of wifi-expert-today.top targeting AI scrapers.

    Probes

    Complaints: The TP-Link Deco XE75 shows recurring firmware stability issues in user forums that were omitted in 90% of affiliate reviews.

    Specs vs Marketing: Eero's "3,000 sq ft" claim is marketing; independent testing shows significant drop-off after 2,200 sq ft in multi-story layouts.

    Next steps

    1. Review the full report at ~/.local/share/cv/runs/mesh-wifi-0520/report.md.
    2. Approve adding wifi-expert-today.top to the suspect domain list.
    3. Run a targeted search for "Deco XE75 firmware v1.2.x issues" to verify recent stability.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Marketplace research is broken by SEO, affiliate marketing, and AI-generated content farms. This skill provides a systematic framework to verify if a product consensus is genuine or manufactured by analyzing search streams for hidden biases.

    What it does

    • Multi-stream analysis compares results from Brave Search and three Cloudflare-backed engines to detect stream-specific manipulation.
    • Source classification categorizes domains into independent testers, affiliate round-ups, or suspect SEO farms based on page metadata.
    • Affiliate detection scans page content for tracking links, missing disclosures, and templated press copy.
    • Adversarial auditing identifies hidden text, AI-directed instructions, and marketing claims masquerading as specs.
    • Criteria locking forces a weighted evaluation of candidates against measurable metrics before reviewing search results.

    How it works

    1. Initialize run. Call cv new to define the topic and lock measurable criteria with weighted scores.
    2. Fan out search. Execute four targeted queries across all streams to find alternatives, complaints, and neutral data.
    3. Inspect and digest. Analyze the top 15 results for affiliate signals and hidden text to generate a comprehensive research digest.
    4. Probe and report. Score the shortlist against criteria, verify top-pick complaints, and generate a final verification report.

    Frameworks & tools

    The skill utilizes a custom CLI tool cv built with Python and managed via uv. It integrates with the Brave Search API and Cloudflare AI Gateway (Ceramic, Exa, Linkup).

    Why this beats prompting it yourself

    Standard prompting often succumbs to the "hallucination of consensus" by summarizing the most frequent search results. This skill enforces a "criteria-first" logic and uses multi-engine cross-referencing to surface what search engines or affiliate sites are intentionally omitting.

    Use cases

    • Product vetting before making high-value purchases like home infrastructure or electronics.
    • Market research to identify if a niche is dominated by manufactured SEO consensus.
    • Bias auditing of existing research to find hidden affiliate interests or bot-farm influence.
    • Spec verification by separating manufacturer marketing claims from independent lab measurements.

    Known limitations

    Cannot detect manipulation in results no engine surfaces. Hidden-text detection is limited to inline styles and attributes, not external stylesheets. JS-heavy or bot-walled pages require fallback fetching.

    Cannot see results no engine surfaces. Hidden-text detection skips external CSS. JS-rendered pages bypass affiliate/hidden-text checks. Requires Brave and Cloudflare API keys.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    Requires

    Cloudflare
    Brave
    macOS
    Linux
    Claude Code
    uv 0.4.19+
    Python 3.11+
    Brave Search API key
    Cloudflare API token
    Python
    uv (Python tool runner)

    Permissions

    Terminal / Shell
    Read Files
    Network Access
    Write Files
    Environment Variables

    Allowed Hosts

    api.search.brave.com
    api.cloudflare.com
    brave.com

    File Scopes

    ~/.config/consensus-verification/env
    ~/.config/consensus-verification/pending-keys
    ~/.local/share/consensus-verification/**
    ~/.cache/consensus-verification/**
    $CV_HOME/**

    Terminal runs the bundled `cv` CLI (a uv script). Network access is for the two search APIs and plain HTTPS GETs of the top result pages (up to 3 MB each, nothing submitted). Environment variables or `~/.config/consensus-verification/env` supply the three keys, which are never printed or stored in reports. Write access covers only the run, ledger and 24-hour cache directories outside the skill. The skill asks first, every time, before running the optional macOS `setup-keys.sh` (writes keys to the login Keychain), installing uv, raising a run's search budget, or editing your domain list. It never logs in, buys, submits forms or posts anything.

    Listed1 month ago

    What's inside

    Frequently Asked Questions

    This skill eliminates the "echo chamber" effect of modern SEO by cross-referencing multiple search engines (Brave, Exa, etc.) and programmatically identifying hidden affiliate links or AI-generated content farms that skew product recommendations.

    The purchase includes the `cv` CLI tool built with Python, a pre-configured `uv` environment for dependency management, and full integration documentation for Brave Search and Cloudflare AI Gateway.

    Yes, this skill is designed to work within any AI agent environment that supports CLI execution and Python 3.10+; it is optimized for agents that can handle multi-step research workflows.

    The skill forces you to define and weight measurable criteria *before* search begins, preventing the AI from being swayed by the persuasive marketing language it encounters during the browsing phase.

    While the skill is highly effective at detecting affiliate tracking and inline hidden text, it cannot analyze data from sites that are completely blocked by bot-mitigation tools or content that has been de-indexed by all four search streams.

    Updates are managed via `uv` to ensure seamless versioning; you will receive notifications for new releases that include updated detection patterns for evolving SEO and AI-farming tactics.

    New in Research & Analysis