Orkestra: Guarded, Test-First Pipeline for Coding Agents

    1

    Runs every coding request through the same local steps: plan, test-first build, gates, review and an evidence report. Blocks commit, push, deploy and secret reads unless you ask.

    Free

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Orkestra: Guarded, Test-First Pipeline for Coding Agents

    Example session with this skill installed

    /orkestra:run add CSV export to the order list

    • Read your context and instructions
    • Compiled the orkestra

    Summary

    Orkestra opened a tracked run, sized it, backed up the uncommitted work, and printed the one next step. The evidence report starts empty and fills in as the run moves.

    $ orkestra start "add CSV export to the order list"
    run started: 001-add-csv-export-to-the-order-list in ~/demo
    size: M (inferred from request; override with --size XS|S|M|L)
    baseline: git, no commits yet · uncommitted files: 1
    NOTE: the working tree already had uncommitted changes. They are backed up and will never be attributed to this run.
    next action: Classify the request (size XS/S/M/L, project, risk) into request.md → `orkestra phase next`.
    suggested classification: Type: feature · Size: M · Risk: medium
    
    $ orkestra watch --once
     phase    intake › discover › clarify › plan › approve › implement › verify › review › deliver › done
     status  ● intake phase open · run state updated 0s ago
    
    $ orkestra next
    next [intake]: classify the request: append `## Classification` to request.md
    why: request.md has no classification yet
    
    Evidence fieldWhat it records
    GatesBaseline vs last verify, per test command
    TasksRed (failing) and green (passing) exit codes
    Test integrityDeleted tests, added skip/only/xfail
    Review triageFixed, deferred, rejected findings
    Commit/push"not done" unless you asked

    Next steps

    • Let the agent continue: it follows orkestra next until the report is written.
    • Run orkestra report evidence at any time to see the machine-written proof.

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

    About this skill

    What it does

    Orkestra walks your coding agent through the same fixed phases on every request: intake, discover, clarify, plan, approve, implement, verify, review, deliver. A local CLI keeps the state and hooks enforce the rules, so the process does not depend on the model remembering it.

    Problems it solves

    • You ask for a change and then read a long diff to find out what the agent touched, skipped or guessed.
    • Agents commit, push or deploy when you did not ask.
    • "Tests pass" with no proof, or tests quietly weakened to go green.
    • Agents writing into the wrong project or reading secret files.

    How it works

    • Hook guards: git commit, push, merge, reset and stash are refused unless your current message asks for them. Reading or writing .env*, private keys and service-account JSON is refused. Deploys, ssh, dependency installs outside the approved plan and writes outside the run's project are refused during a run.
    • Test-first evidence: each task records a failing test (red) and then a passing one (green). The test cannot change between the two, and deleted tests or added skip/only/xfail are flagged.
    • No-regression gates: your project's test commands run before and after the change; a regression blocks delivery.
    • Agent team: read-only scouts, an architect, a plan critic, a TDD implementer, a reviewer, an adversarial tester and a verifier, each with a fixed role.
    • Cost-aware: small requests take a short path with no scouts, no plan critic and no per-task review. Cheap models do mechanical work and the strongest model is kept for planning and the final review.
    • Live view: orkestra watch and orkestra next show the phase, the activity and the one next step.

    Who it is for

    Developers who use Claude Code, Cursor, GitHub Copilot CLI or Pi and want the same disciplined process every time, with proof instead of promises.

    Free and open source

    MIT license, Python standard library only, no telemetry, nothing leaves your machine except what your model provider's own client sends.

    Guards are filters on tool calls, not a sandbox: the agent still runs as you, on your files. Shell guards read commands without running them, so obfuscated commands can slip through (the activity log shows them afterwards). Claude Code and Cursor hooks fail open if the hook crashes; Copilot fails closed. The proof is only as strong as your project's tests: a project without tests has no regression net. Windows is less tested than macOS and Linux.

    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 today

    • Free with an Agensi account

    Requires

    GitHub
    Python 3.9+
    Git
    Orkestra CLI (free, github.com/soft-ai-solutions/orkestra)
    Claude Code
    Cursor
    GitHub Copilot

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Network Access

    Allowed Hosts

    github.com

    File Scopes

    .orkestra/**
    ~/.orkestra/**

    Terminal: runs the orkestra CLI and your project's own test commands. Read/Write Files: the agent edits your project; run state is kept in .orkestra/ and ~/.orkestra/. Network: only git clone of the open-source repo during install. Hooks refuse secret-file reads, commits, pushes and deploys unless you ask.

    Listedtoday

    What's inside

    Frequently Asked Questions

    Yes, the free Orkestra CLI (Python 3.9+, standard library only, nothing to pip install). The skill checks for it and shows the install steps; it never runs the installer without your yes. python3 install.py --uninstall --purge removes everything.

    No. git commit, push, merge, reset and stash are refused unless the message you just sent asks for them, for example "commit this". The permission is for that message only.

    It is built to keep it down. Small requests skip the extra agents, mechanical work goes to cheaper models, the strongest model is kept for planning and the final review, and loops stop after three tries without new evidence.

    New in Agents & Orchestration