Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    19 — Witness-Eater · Complete Edition

    1

    Retains support-dependency analysis and evidence-removal tests, adding citation-family checks, recommendation reviews and clear confidence statements.

    $25

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    19 — Witness-Eater · Complete Edition

    19 — Witness-Eater · Complete Edition

    Example session with this skill installed

    Everyday request

    This recommendation cites three reports, but two copied the same original source. Show what the conclusion really depends on.

    For a reproducible local example, use the included synthetic structured fixture:

    {
      "sources": [
        {
          "id": "original"
        },
        {
          "id": "copy",
          "depends_on": [
            "original"
          ]
        },
        {
          "id": "independent"
        }
      ],
      "claims": [
        {
          "id": "only-copy",
          "support_sets": [
            [
              "copy"
            ]
          ]
        },
        {
          "id": "alternative",
          "support_sets": [
            [
              "copy"
            ],
            [
              "independent"
            ]
          ]
        }
      ]
    }
    

    Run the class's packaged helper on that fixture. Show the readable result, full structured output, executed Thirsty calculation and the limits of what was demonstrated.

    • Read your context and instructions
    • Compiled the output

    Witness-Eater — real local worked example

    Example type: Actual execution of the packaged structured helper on synthetic input. This is not a claimed live customer session or a full specialist-model benchmark.

    Readable work product

    Declared support-removal trials:
    - Remove original: claims losing support = only-copy
    - Remove copy: claims losing support = only-copy
    - Remove independent: claims losing support = none
    Declared dependency logic; does not establish that a source is truthful or a claim is true
    

    Complete structured result

    {
      "baseline_claims": [
        "only-copy",
        "alternative"
      ],
      "boundary": "Declared dependency logic; does not establish that a source is truthful or a claim is true",
      "removal_trials": [
        {
          "claims_losing_declared_support": [
            "only-copy"
          ],
          "remove": "original"
        },
        {
          "claims_losing_declared_support": [
            "only-copy"
          ],
          "remove": "copy"
        },
        {
          "claims_losing_declared_support": [],
          "remove": "independent"
        }
      ]
    }
    

    Executed Thirsty-lang calculation

    module conclave: core
    
    drink result = 2
    pour result
    

    The helper checked the language result independently, encoded the complete structured result using the published TSCG-B codec, decoded it and compared the text. Running the standalone helper generates the result files and execution receipt. The example shown here was produced on the supplied synthetic input.

    The deeper specialist use

    Request: A recommendation cites a report that copied an original source, plus an independent source. Determine what its declared support really depends on.

    Illustrative specialist response: Build the claim-to-source and upstream-dependency map before counting citations. Remove the original source in an isolated logical trial: its derivative report loses availability too. A claim supported only by that derivative loses declared support; a claim with an independent alternative may retain it. Keep the claim and acceptance rule fixed. This identifies dependencies in the supplied support model, not whether a source is truthful or a conclusion is correct.

    The preceding specialist response is an authored illustration, not an executed external action. The original class procedures and supporting skills remain included for an actual authorized assignment.

    Next step

    Replace the fixture with your own task data after checking that it fits the helper's input model, or use the conversational workflow directly with your AI host. Use a fresh output directory; the helper refuses to overwrite an existing result. Review factual classifications and missing inputs before relying on the result.

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

    About this skill

    Witness-Eater — Complete Edition

    Find out what the evidence is actually holding up.

    Retains support-dependency analysis and evidence-removal tests, adding citation-family checks, recommendation reviews and clear confidence statements.

    One class. 47 equipped skills. The original specialist method plus six practical everyday workflows. $25 as a one-time purchase.

    For checking reports, research notes, recommendations and evidence-heavy decisions. For deeper work, the class retains its original specialist equipment and source-defined method: Which evidence is actually necessary for the claimed acceptance?

    What you actually receive

    • All 40 original skills, including the specialist entrypoint, original supporting procedures, language workbench and evaluation lab.
    • Six added everyday skills, listed in full below, and the new structured helper and worked example.
    • 1 restored named dependency/dependencies: epistemic-status-enforcer.
    • Class methods, contracts, source references, standalone task-packet tooling, executable helpers and worked examples, delivered through your connected AI.
    • Standalone Thirsty-lang and TSCG-B tooling that uses the real thirsty-lang==0.9.0 runtime. Code execution requires Python 3.10+, a host execution tool and that separately installed package in the same environment. No runtime wheel is delivered through Agensi.

    The specialist class: the original depth stays equipped

    1. Freeze originals and create isolated copies with explicit provenance.
    2. Build evidence-to-claim dependencies and identify shared upstream sources.
    3. Run the baseline verifier and retain the exact observed result.
    4. Remove or substitute one authorized evidence element or dependency group at a time.
    5. Re-run the frozen verifier with fixed conditions and record acceptance changes.
    6. Minimize useful counterexamples without changing the claim or oracle.
    7. Report indispensable, redundant, dependent and untested support, with replay instructions.

    Specialist deliverable: support_dependency_map. Its source-defined result fields are baseline_verdict, ablation_trials, support_edges, shared_sources, minimal_counterexamples, coverage. These guide the work product; an actual outcome requires the task inputs, authorized tools and evidence.

    Six everyday workflows — the documented practical use cases

    1. Connect each important claim to its actual support

    Extract claims separately from citations and map the supporting passages. Record gaps, source dates and the distinction between support and truth.

    2. Spot several citations that are really one source

    Trace declared upstream references and distinguish repeated reporting from independent confirmation. Do not infer independence from different URLs alone.

    3. Test whether a conclusion survives losing a source

    Freeze the claim and declared support logic, remove one source or dependency group, and record which claims lose support.

    4. Check the foundation of a recommendation

    Separate facts, preferences and reasoning; identify which unsupported premise could change the recommendation. Keep the user’s value choices explicit.

    5. Write a confidence statement the evidence can support

    Describe completeness, independence, directness and unresolved contradictions without inventing numeric confidence.

    6. Find the support a decision cannot do without

    Use explicit support sets and upstream dependencies to identify indispensable sources. Preserve originals and report untested alternatives.

    Example 1 — what a specialist assignment can look like

    You ask: A recommendation cites a report that copied an original source, plus an independent source. Determine what its declared support really depends on.

    Illustrative response: Build the claim-to-source and upstream-dependency map before counting citations. Remove the original source in an isolated logical trial: its derivative report loses availability too. A claim supported only by that derivative loses declared support; a claim with an independent alternative may retain it. Keep the claim and acceptance rule fixed. This identifies dependencies in the supplied support model, not whether a source is truthful or a conclusion is correct.

    This example illustrates the class method. It is not an assertion that the proposed external investigation, model trial or system change has been executed.

    Example 2 — an everyday request

    This recommendation cites three reports, but two copied the same original source. Show what the conclusion really depends on.

    The work product: A claim-to-source map, shared upstream dependencies, removal tests, and the evidence whose absence would change the result.

    The included local helper demonstrates a bounded part of this workflow. Its actual run on synthetic structured input produced:

    Declared support-removal trials:
    - Remove original: claims losing support = only-copy
    - Remove copy: claims losing support = only-copy
    - Remove independent: claims losing support = none
    Declared dependency logic; does not establish that a source is truthful or a claim is true
    

    See the demo section below for its complete input, structured result and executed Thirsty calculation.

    Example 3 — using the class template on your own material

    Use Witness-Eater — Complete Edition.
    Goal: [the concrete result I need]
    Material: [paste or attach the actual records, notes, code or facts]
    Scope: [what may be inspected or changed]
    Constraints: [time window, dependencies, formats and important conditions]
    Deliver: A claim-to-source map, shared upstream dependencies, removal tests, and the evidence whose absence would change the result.
    Use the original specialist method when the problem requires it.
    Ask only for missing facts that materially change the result.
    Show what you actually did and what still needs a decision.
    

    For a simple request, use only the relevant everyday mode. For advanced work, select the original specialist procedures. Keeping the equipment available does not require loading every skill into every interaction.

    Every skill available in this pack (47 total)

    • architecture-decision-recorder — Edition XXII source-attributed supplemental agent procedure: Architecture choice and tradeoff recording.

    • build-reproducibility-receipts — Create verifiable local build and test receipts linking source snapshots, commands and exact artifact bytes.

    • ceta-class-router — Choose a Thirstforged Conclave sub-agent class for a CETA task, prepare its bounded assignment and exact skill inventory, and distinguish instruction packets from native profile activation.

    • ceta-cross-representation-meaning-trials — Test whether intent, obligations, schemas, UTF representations, and implementation preserve the same supported meaning, including negative and ambiguous cases.

    • ceta-delegation-collusion-trials — Construct bounded delegation and review graphs that test circular approval, identity aliasing, authority laundering, and coalition behavior against actual acceptance rules.

    • ceta-evidence-cross-examination — Cross-examine a Thirstforged Conclave result against raw observations, exact source bindings, expected predicates, and actual reviewer identity before integration.

    • ceta-heldout-loadout-trials — Compare Chimera Foundry loadouts against a fixed baseline on preserved held-out tasks and report supported advantage, regression, or inconclusive evidence.

    • ceta-utf-contract-map — Map a CETA task to the six Universal Thirsty Family tiers and exact isolated Thirsty-Lang 0.9.0 tools, preserving the difference between analysis, integrity, and authority.

    • codex-acceptance-crosswalk — Use for map source-defined requirements to executable acceptance evidence.

    • codex-access-control-verifier — Use for inspect configured least-privilege checks and insecure access exposure.

    • codex-api-contract-auditor — Use for inspect api definition documents, json contracts and documentation consistency.

    • codex-approval-trace — Use for trace decision, requester, scope, expiry, and evidence receipts.

    • codex-autonomy-review — Use for evaluate competence evidence and legitimate authority for autonomy changes.

    • codex-build-reproducer — Use for inventory local build ingredients and reproducibility conditions.

    • codex-claim-integrity — Use for prevent observed/inferred/proposed/implemented states from being conflated.

    • codex-data-lineage — Use for trace source-data provenance and evidence status through transformations.

    • codex-dependency-mapper — Use for inspect dependency and integration surfaces with scoped evidence.

    • codex-evidence-ledger — Use for validate referenced evidence paths and source identity.

    • codex-hostile-review — Use for challenge the implementation for bypass, risk, and missing negative evidence.

    • codex-identity-verifier — Use for review verified identity boundary instead of treating familiarity as authentication.

    • codex-independent-verifier — Use for separate implementer checks from independent repeatable verification.

    • codex-integration-test-auditor — Use for inspect integration test entrypoints and source dependencies.

    • codex-operations-support — Use for diagnose support cases using actual logs and local help documentation.

    • codex-python-verifier — Use for run offline python syntax and static risk checks without executing repository code.

    • codex-repo-preservation — Use for protect untracked work, check provenance and refuse destructive cleanup.

    • codex-runtime-architecture — Use for inspect declared runtime entrypoints, interlocks and operational boundaries.

    • codex-runtime-health — Use for inspect health-related logs and configs as static evidence, not live monitoring.

    • codex-sandbox-boundaries — Use for inspect process execution and file permission indicators locally.

    • codex-scope-guardian — Use for prevent invented or silently widened objectives and repository scope.

    • codex-source-integrity — Use for check bundled source document checksums and protect observed provenance.

    • conclave-evaluation-lab — Design held-out comparisons of the equipped agent and baseline workflows with matched models, tools, budgets, and recorded evidence.

    • conclave-language-workbench — Use Thirsty-lang as the primary local language and TSCG-B to encode/decode exact UTF-8 task and result text.

    • conclave-witness-eater — Retains support-dependency analysis and evidence-removal tests, adding citation-family checks, recommendation reviews and clear confidence statements.

    • epistemic-status-enforcer — Apply explicit epistemic status to meaningful claims.

    • identity-continuity-auditor — Edition XXII source-attributed supplemental agent procedure: Continuity and principal identity auditing.

    • polyglot-stack-selector — Select practical combinations of programming languages and runtime boundaries for one application.

    • proof-obligation-generator — Edition XXII source-attributed supplemental agent procedure: Execution proof obligation construction.

    • property-fuzz-test-engineer — Implement executable property-based tests, deterministic fuzz harnesses and failure minimization for source code.

    • python-production-coder — Implement and repair working Python applications, libraries and asynchronous services.

    • thirsty-work-orchestrator — Edition XXII source-attributed supplemental agent procedure: Role graph scheduling and evidence handoff.

    • type-contract-architect — Create implementable domain types and API contracts before coding.

    • witness-eater-citation-family — Spot several citations that are really one source.

    • witness-eater-claim-source-map — Connect each important claim to its actual support.

    • witness-eater-evidence-removal — Test whether a conclusion survives losing a source.

    • witness-eater-minimal-support — Find the support a decision cannot do without.

    • witness-eater-recommendation-audit — Check the foundation of a recommendation.

    • witness-eater-report-confidence — Write a confidence statement the evidence can support.

    Thirsty-lang and TSCG-B in practice

    Run the packaged helper with Python 3.10+ to generate a readable result, structured JSON, the executed .thirsty calculation, a binary .tscg-b result and an execution receipt. The helper executes supported arithmetic in Thirsty-lang and independently checks the result; Python handles structured input and the domain algorithm. TSCG-B preserves result text through binary encode/decode. A valid frame does not itself prove the text is true or authorize an action.

    Preservation and validation

    Every original skill identity and the specialist methods remain, together with the six everyday additions and repaired named dependencies. The Agensi upload layout adapts executable scripts and reference delivery; historical source files and preservation records remain in the creator's original archive.

    The repaired collection passed 409 local delivery and execution checks, including all 19 standalone class helpers, real Thirsty-lang calculations, TSCG-B round trips, exact task packets, delivery limits and negative cases. Independent checks also passed all 52 distinct audit-tool bindings and their source-index lookups. Six compiler-specific examples were not executed because their compiler dependencies were absent. These results do not establish every AI host's behavior, marketplace approval, live buyer retrieval, frontier-model superiority or revenue.

    Start using it

    Connect your AI to Agensi and ask: “Use my Agensi skill 19 — Witness-Eater · Complete Edition. My goal is [result]. Here is my actual material: [notes, records or code].” The pack provides an index; your AI loads the class entrypoint skills/conclave-witness-eater/SKILL.md, then loads the supporting skills relevant to your task. Purchasing the pack does not automatically run all its skills at once.

    Text and reasoning workflows run through your existing AI. Standalone scripts additionally require Python 3.10+ and a code execution tool. Thirsty-lang and TSCG-B execution requires thirsty-lang==0.9.0 installed separately in that environment; your AI should explain missing requirements before starting. Scripts are fetched unchanged through Agensi, executed temporarily and removed. Task result files can be delivered to you; the purchased skill is not installed as a downloadable local folder.

    Image, video, voice and data services from Agensi's optional tools catalog are separate paid services. This pack does not require adding those services merely to use its text workflows or Python helpers. External actions, compiler tasks and account access still require the actual relevant host tools and your permission.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Research & Analysis.

    This is a skill/class package for an existing compatible AI host. It does not supply model weights, hosted compute, API credits, automatic account connections or permissions. The included helpers accept bounded structured inputs; they are not general document parsers or substitutes for semantic review. Their actual synthetic-fixture outputs are distinguished from authored specialist illustrations. Local preservation/tool checks do not establish correctness on arbitrary tasks, frontier-model superiority, customer results or revenue. Optional UTF analysis features may require additional dependencies. Marketplace ingestion of the final multi-skill ZIP remains subject to the receiving platform’s actual review.

    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 buying a skill.

    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 5 days ago

    Software
    Node.js
    Optional
    Python 3.10+thirsty-lang==0.9.0

    Text workflows use your connected AI. Code needs Python 3.10+ and an execution tool. Thirsty-lang and TSCG-B need thirsty-lang==0.9.0 installed in that environment. No hosted model or API credits are included.

    Permissions

    Terminal / Shell
    Read Files
    Write Files

    Read Files, Write Files and Terminal/Shell support the optional local examples and authorized project work. Work stays within the user-approved scope. Browser, network, services and credentials are task-dependent and are not granted by this package. A draft, recommendation or prepared payload is not evidence of an external action.

    Listed5 days ago

    What's inside

    Frequently Asked Questions

    This listing is for Witness-Eater — Complete Edition: one specialist class package with 47 skills, all 40 original skills retained, six added everyday workflows, repaired named dependencies, tools, references and worked examples. It is a one-time purchase, not a monthly subscription. Host-model usage and third-party service charges are separate.

    Every original skill identity and specialist procedure remains, with six everyday additions. Executable helpers and reference layout were adapted for Agensi temporary-file delivery. The creator retains the historical sources and preservation records separately.

    For checking reports, research notes, recommendations and evidence-heavy decisions. The everyday modes can be used conversationally with supplied notes, facts or records. Advanced technical tasks and executable utilities require the relevant tools and environment.

    Connect your AI to Agensi, ask it to use this pack by name, and provide your actual goal and material. It loads the class entrypoint and then the supporting skills needed for the task. The pack is selected on demand; all skills do not run automatically at purchase.

    The structured helper example was actually executed on synthetic input, with real Thirsty-lang execution and a TSCG-B round trip. Running the helper generates result files and a receipt. The specialist scenario is labeled illustrative. No live customer outcome, marketplace buyer test or unrun model benchmark is claimed.

    This purchase supplies the listed class package for an existing compatible AI host. It does not supply model weights, hosted compute, API credits or all 19 Conclave agents. Other class packages are separate.

    Text workflows use the connected AI. Script execution needs Python and an execution tool; language and codec operations additionally need thirsty-lang==0.9.0. No bundled binary runtime, model, API credits or automatic account connections are supplied. Advanced tasks need the relevant compiler, browser, file or account tools and your permission. The pack itself grants none of those tools.

    New in Research & Analysis