Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Codex Taskforce

    1

    Token-efficient Codex orchestration with specialized agents, independent verification, persistent project context, and compact evidence reports.

    Free

    2 usesSecurity scanned
    Codex Taskforce

    Codex Taskforce

    Example session with this skill installed

    Initialize a Taskforce to refactor the authentication module. Assign an Investigator to find the bottlenecks and an Executor to implement the fixes.

    • Read your context and instructions
    • Compiled the codex taskforce

    I have initialized the Taskforce for the authentication module refactor. Project context has been resolved, and Task ID TF-AUTH-001 is now active. The Investigator is currently mapping the bottlenecks in the middleware stack.

    Taskforce Status: TF-AUTH-001

    RoleStatusAssignmentEvidence / Output
    ArchivistActiveInitializing agent_docs/project_map.mdCreated project context root.
    InvestigatorRunningAnalyzing src/auth/*.ts for latencyIdentified 200ms delay in JWT verification.
    ExecutorQueuedImplement caching for public keysAwaiting Investigator report.
    TesterQueuedVerify fix with load test scriptAwaiting implementation.

    Next steps

    1. Review the Investigator's findings in agent_docs/investigations/auth_latency.md once complete.
    2. Approve the Executor's implementation plan for public key caching.
    3. Monitor the Archivist's closure report for updated integration gates.

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

    About this skill

    A coordinated agent team for substantial work

    Built for token-efficient agent orchestration, with swarm execution, persistent project context, and compact knowledge handoffs between agents.

    Codex Taskforce keeps the main agent responsible for direction, architecture, scope, synthesis, integration gates, and acceptance. Specialized workers handle bounded implementation, operational checks, research, independent verification, and documentation.

    What makes it useful

    • Knowledge-bearing task capsules give each worker the ownership, evidence, guidance, and acceptance intent needed to work independently.
    • Compact evidence-linked reports and batched decisions reduce operational noise in the main conversation.
    • Six roles cover Explorer, Investigator, Executor, an optional Senior Executor, Tester, and Archivist. Use only the roles a task needs.
    • Independent verification keeps production repair with its owning Executor and acceptance decisions with the main agent.
    • Persistent project memory in agent_docs/ records goals, architecture, decisions, progress, and session handoffs.
    • A bundled reporter produces a six-column per-role token table from available local Codex session evidence.

    Included

    One standalone skill, orchestration and dispatch instructions, six worker role resources, configurable model profiles, six project-context templates, a non-overwriting project initializer, and a local token reporter. Five default worker profiles use GPT-6 Luna; the optional Senior profile uses GPT-6.1 Sol. Explicit user model choices take precedence.

    Requirements

    Local Codex with native subagent tools, per-worker model/reasoning selection, and the filesystem/tool access required by the task. Python 3.11+ is required for the bundled helpers. Access to the configured models must be supplied by the user's Codex account/provider.

    Permissions and limitations

    The initializer is read-only by default and creates only missing agent_docs/ documents when setup is authorized. Existing documents, AGENTS.md, Codex settings, and Git state are preserved. Role instructions are passed in memory; no worker configuration is installed.

    The reporter reads local session metadata, token counters, and deployment boundaries. The bundled helpers make no outbound requests and do not upload session content.

    This is an instruction-based workflow, not a deterministic engine or an independent sandbox. It targets main-agent overhead; total worker tokens may increase, and no fixed savings percentage is guaranteed. Token reporting depends on readable local JSONL evidence and a supported schema.

    Through Agensi MCP, linked references and permitted script execution must be exposed to Codex and/or its workers. Missing capabilities are reported rather than bypassed. Local packaging and synthetic filesystem/reporting checks passed; live Agensi MCP execution and a full multi-agent task replay have not yet been verified.

    Use it for substantial feature work, difficult investigations, non-overlapping module changes, and recoverable project handoffs.

    Codex only; requires the native subagent/model controls described above. This is an instruction-based workflow, not a deterministic engine or separate sandbox. No fixed token or quota saving is guaranteed; aggregate worker tokens can increase. Token reporting needs local JSONL evidence and a supported schema. Live Agensi MCP resource/script delivery and a complete multi-agent task replay have not yet been verified. Missing capabilities or usage evidence are reported explicitly.

    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

    2 uses

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    • Free with an Agensi account

    Requires

    Codex
    Python 3.11+
    Python

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Environment Variables
    Browser
    Network Access

    Terminal and file access support assigned project work and the bundled helpers. The initializer creates only missing agent_docs/ outputs when authorized. Token reporting reads local Codex session records and CODEX_THREAD_ID/CODEX_HOME, without uploading them. Browser/network access is conditional on the user's task, such as solution research or browser verification; the bundled Python helpers make no outbound requests. Effective permissions remain those of the parent Codex session.

    Listed1 month ago

    What's inside

    Frequently Asked Questions

    This product targets local Codex only. It requires native subagent creation, steering, result collection, task naming, and per-worker model/reasoning selection. The SKILL.md file format is portable, but this workflow has not been validated on Claude Code, Cursor, or other agents.

    New in Agents & Orchestration