Readable Work-Intent Contract for Orchestrators and Fleets

    1

    When a worker machine runs jobs from somewhere else, its owner should be able to read what each job is for.

    $29

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Readable Work-Intent Contract for Orchestrators and Fleets

    Example session with this skill installed

    Validate this job description before I send it to the render fleet: {"schemaVersion":1,"title":"task-4471","project":"Forest cartoon","purpose":"Produce the forest scene for the final cartoon","stage":"Rendering","expectedOutput":"120 image frames"}

    • Read your context and instructions
    • Compiled the readable work-intent contract

    Summary

    Rejected: title is an identifier, not a description.

    Detail

    • node -e with validateWorkIntent -> Error: Provide a readable title (8-160 characters); identifiers and empty placeholders are not descriptions.
    • python3 -I scripts/work_intent.py validate job.json -> INVALID with the same reason (exit 1); both implementations agree.

    Fix

    Replace the title with what the job is, for example "Render cartoon episode 1, scene 4, frames 120-239". Re-validated: VALID. A worker showing this queue will display that sentence; a legacy worker would have shown "Description unavailable - producer update required" instead of the id.

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

    About this skill

    When a worker machine runs jobs from somewhere else, its owner should be able to read what each job is for. Left alone, producers send task-4471, a UUID, or "unknown". This contract makes the description a validated object and makes both of your implementations agree on what passes.

    The contract (reference/contract.md): schemaVersion 1 plus title (8-160), project (2-80), purpose (12-600), stage (2-80), expectedOutput (6-400) and optional parentTitle. A field is readable only when it is trimmed, within its UTF-16 length range, well-formed, contains a letter, carries no control, BOM, zero-width or bidirectional characters, is not an identifier (digit runs, 16+ hex, UUIDs, or those prefixed with session/task/job/lease/pid/thread/run/build) and is not a placeholder. Unknown fields such as command or permissions fail with their names listed: this object describes work, it never authorizes it.

    Parsing: 8192-byte cap before parsing; duplicate top-level keys rejected even with equal values and even when the second key is spelled with JSON unicode escapes, because JSON.parse silently keeps the last one; returned object frozen.

    Legacy projection: legacyTitle() keeps a readable label or your own policy's explicit "withheld" marker and replaces everything else with "Description unavailable - producer update required", so a queue never shows an id.

    Two implementations, one fixtures file: work-intent.mjs (Node 20+) and work_intent.py (Python 3.9+, with a validate <file> CLI). 29 Node tests including a cross-check that runs the 5-test Python suite on the same fixtures. No packages, no network.

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

    Lexical checks only; does not verify truthfulness of prose. Placeholder lists are English-centric. Requires manual porting of new rules to both Node and Python files.

    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 18 days ago

    Software
    node python3Python

    Permissions

    Terminal / Shell
    Read Files

    Pure validation library plus a CLI that reads one JSON file. No network, no environment variables, no writes.

    Listed18 days ago

    What's inside

    Frequently Asked Questions

    This skill replaces cryptic IDs (like UUIDs) with a mandatory five-field human-readable schema. It prevents system owners from being 'blind' to what their agents are doing by enforcing descriptive titles, purposes, and outputs for every task.

    The skill includes standalone, zero-dependency implementations for both Node.js (20+) and Python (3.9+). Because it is framework-agnostic, it can be integrated into any orchestration layer or agentic workflow that uses these languages.

    Yes, the skill is designed to detect and block hidden identifiers, digit runs, hex strings, and malicious formatting like zero-width spaces. This ensures producers cannot 'smuggle' machine-only commands into fields meant for human operators.

    You receive the full source code for both Node.js and Python versions, a shared test fixture for cross-platform consistency, and a CLI audit tool for use in your CI/CD pipelines.

    Integration is straightforward: use the provided validation function on your 'producer' agents before they send tasks and the parsing function on your 'worker' agents. It requires no external package installations.

    While it enforces lexical readability and blocks non-human identifiers, it does not perform semantic 'truth' checks. It ensures a description looks like English prose, but it cannot verify if the agent is being honest about its intent.

    New in Agents & Orchestration