More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    DAG orchestrator skill

    1

    Enterprise multi-agent DAG orchestrator with 4-tier epistemic conflict resolution and cryptographic provenance.

    Free

    Security scanned
    DAG orchestrator skill

    DAG orchestrator skill

    Example session with this skill installed

    Does ACME exposure breach the risk threshold, and does the pricing guardrail allow the re-price? Cite the policies.

    • Read your context and instructions
    • Compiled the dag orchestrator

    I have processed the compound analytical query by compiling a 3-wave execution DAG and reconciling data across the Tier 1 compute and Tier 2 policy engines.

    Orchestrator Synthesis

    Request ID: req-8829-xf
    State Fingerprint: 8f2d93a1...

    ComponentStatusDetails
    Tier 1 ComputeOKCurrent ACME Exposure: $4.2M.
    Tier 2 PolicyOKRule 57 (Risk Threshold): $5.0M. Rule 112 (Pricing): Allowed.
    Conflict ResolutionResolvedTier 1 compute metrics prioritized over Tier 3 retrieval variance.
    ProvenanceVerifiedAll citations matched vector_chunk_sha256 in the Protected 50 corpus.

    Triggered Policies

    • Policy 1.2.4 (Quantitative Risk): Exposure of $4.2M is within the $5.0M threshold. Verdict: PASS.

    Policy 5.1.0 (Pricing Guardrail): Entity ACME is eligible for re-pricing under active identity ACTIVE_200. Verdict:

    ALLOW.

    Telemetry Summary

    • Total Latency: 1240ms (p50 target met).
    • Execution Waves: 3.
    • Budget Slack: 1360ms.

    Next steps

    • Review the provenance_ledger for specific document IDs associated with Rule 57.
    • Check the slm_shadow_telemetry logs for intent agreement rates.
    • Proceed with the re-pricing workflow as authorized by the symbolic AST engine.

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

    About this skill

    Complex analytical queries often fail when they require data from multiple conflicting sources or exceed latency budgets. This skill provides a high-assurance orchestrator that compiles multi-hop queries into validated Directed Acyclic Graphs (DAGs) while enforcing strict enterprise guardrails.

    What it does

    • DAG Compilation transforms complex tasks into parallel execution waves using Kahn's algorithm to prevent cycles.
    • Epistemic Reconciliation resolves conflicts between different data sources using a 4-tier hierarchy where deterministic compute always overrides unstructured retrieval.
    • Provenance Verification performs cryptographic SHA-256 checks on every retrieved data chunk to prevent spoofing or unauthorized data access.
    • SLA Enforcement prunes optional low-priority tasks to keep end-to-end latency within defined p95 and p99 millisecond targets.
    • Context Compression uses a knapsack algorithm to fit the most relevant facts into a 4096-token window while pinning high-priority data.

    How it works

    1. Intent Routing detects compound multi-hop analysis requests and triggers the DAG planner.
    2. Task Decomposition partitions the query into discrete nodes with assigned priorities, timeouts, and dependencies.
    3. Parallel Execution dispatches subtasks across MCP tools with circuit breakers and adaptive concurrency limits.
    4. Conflict Synthesis merges results, applying the epistemic hierarchy to discard low-confidence or contradictory claims.

    Frameworks & tools

    Built with Python 3.11 using asyncio.TaskGroup and Pydantic v2 for frozen data contracts. It integrates with external systems via MCP, targeting Qdrant, PostgreSQL, and vLLM backends.

    Why this beats prompting it yourself

    Standard prompts cannot guarantee cycle-free task execution or enforce millisecond-level latency budgets across multiple tool calls. This skill replaces unreliable "chain of thought" with a structural execution engine that handles circuit breaking, hedging, and cryptographic provenance checks that prompts alone cannot perform.

    Use cases

    • Risk Exposure Analysis calculating breach thresholds by synthesizing real-time financial metrics with static regulatory policies.
    • Conflict Resolution reconciling disagreeing facts between a vector database and a symbolic policy engine.
    • High-Throughput Analytics managing 60+ subtasks simultaneously without exceeding API rate limits or context windows.

    Known limitations

    Currently prohibited from production connections pending Architecture Review Board audit. Uses a synthetic 550-identity corpus and in-process reference transports instead of live database drivers.

    The vector provenance digest strictly covers chunk text rather than metadata, and natural language prompt-injection screening must be handled at your API gateway.

    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

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 7 days ago

    • Free with an Agensi account

    Requires

    Python

    Permissions

    Terminal / Shell
    Network Access
    Read Files
    Write Files

    File Scopes

    reference/**/*.md
    evals/**/*.json

    This skill enforces a hard 3000ms execution SLA and requires an environment capable of running asynchronous Python 3.11+ tasks.

    Listed7 days ago

    What's inside

    Frequently Asked Questions

    This skill replaces unreliable 'chain-of-thought' prompting with a structural execution engine that uses Kahn’s algorithm to prevent logic cycles and enforces strict p95 latency targets through automated task pruning. It is specifically designed for enterprise environments where data conflicts between multiple sources must be resolved using a deterministic hierarchy.

    The skill is built for Python 3.11+ environments using Pydantic v2 and asyncio. It integrates seamlessly with any agent framework supporting the Model Context Protocol (MCP), specifically optimized for Qdrant, PostgreSQL, and vLLM backends.

    The '4-tier epistemic hierarchy' is a conflict resolution logic that prioritizes data based on its source type; for example, it ensures that verified deterministic compute results always override potentially hallucinated unstructured retrieval data during the synthesis phase.

    You receive the core orchestrator logic, Pydantic data contracts for task decomposition, and the cryptographic provenance module. Please note that it currently includes a synthetic identity corpus for testing, as live database drivers are pending typical enterprise architecture audits.

    The orchestrator uses a specialized knapsack algorithm to prioritize and 'pin' the most critical facts, compressing the execution context into a 4096-token window to ensure high-priority data is never truncated during complex multi-hop queries.

    No, it exclusively compiles and delegates read-only analytical queries across heterogeneous sub-agents.

    New in Agents & Orchestration