{
  "format": {
    "name": "winskel-public-facts",
    "version": "1.1",
    "note": "Winskel's own public facts format. It is not an industry standard."
  },
  "updated": "2026-10-06",
  "product": {
    "name": "Winskel",
    "description": "Winskel is a multi-model coding orchestrator for macOS that coordinates coding work across Claude Code and Codex.",
    "website": "https://www.winskel.com/",
    "agentReference": "https://www.winskel.com/agents",
    "agentReferenceMarkdown": "https://www.winskel.com/agents.md",
    "llmsTxt": "https://www.winskel.com/llms.txt"
  },
  "release": {
    "stage": "Beta",
    "stageNote": "The website calls the current public stage the Beta. The downloadable build is an alpha channel build, and some screens in the app say Alpha.",
    "version": "0.7.0-alpha.1",
    "channel": "alpha",
    "operatingSystems": [
      "macOS 12 or later"
    ],
    "architectures": [
      "arm64 (Apple Silicon)"
    ],
    "notSupported": [
      "Intel Macs",
      "Windows",
      "Linux"
    ],
    "signing": "The build is not signed with an Apple Developer ID and is not notarized by Apple. macOS asks the user to approve the first launch.",
    "updates": "No automatic updates. New builds come from winskel.com.",
    "downloadPage": "https://www.winskel.com/#download",
    "downloadUrl": "https://www.winskel.com/download/Winskel-0.7.0-alpha.1-arm64.dmg",
    "downloadLabel": "Download for Mac",
    "installGuide": "https://www.winskel.com/docs/install"
  },
  "requirements": [
    {
      "item": "A Mac with Apple Silicon running macOS 12 or later",
      "required": true,
      "detail": "Intel Macs, Windows, and Linux are not supported.",
      "source": "https://www.winskel.com/docs/install"
    },
    {
      "item": "A Google account",
      "required": true,
      "detail": "Winskel accounts sign in with Google.",
      "source": "https://www.winskel.com/docs/install#sign-in"
    },
    {
      "item": "Claude Code installed and signed in",
      "required": true,
      "detail": "Winskel plans every objective with Claude Code, so work cannot start without it. Keep Claude Code open on the Mac; Winskel detects the local app and connects automatically.",
      "source": "https://www.winskel.com/docs/connect-claude-code"
    },
    {
      "item": "Codex installed and signed in",
      "required": false,
      "detail": "Needed for routes that use Codex. Keep Codex open on the Mac; Winskel detects the local app and connects automatically.",
      "source": "https://www.winskel.com/docs/connect-codex"
    },
    {
      "item": "A Git repository the user is authorized to change",
      "required": true,
      "detail": "A local Git repository, or one cloned from GitHub. GitHub is optional. Setting up Git for a plain folder is not in the current public download; it is in the next release.",
      "source": "https://www.winskel.com/docs/projects-worktrees"
    },
    {
      "item": "An active provider plan for each agent used",
      "required": true,
      "detail": "An Anthropic plan for Claude Code (required), and an OpenAI plan for Codex only if Codex is used. Their subscriptions, usage limits, and charges are separate from Winskel.",
      "source": "https://www.winskel.com/docs/provider-limit"
    },
    {
      "item": "Free disk space for Git worktrees",
      "required": true,
      "detail": "Each run gets its own Git worktree on the Mac.",
      "source": "https://www.winskel.com/docs/projects-worktrees"
    }
  ],
  "providers": [
    {
      "name": "Claude Code",
      "vendor": "Anthropic",
      "required": true,
      "check": "claude --version",
      "signIn": "claude auth login",
      "role": "Required. Winskel plans every objective with Claude Code and can give work to Claude Code models.",
      "source": "https://www.winskel.com/docs/connect-claude-code"
    },
    {
      "name": "Codex",
      "vendor": "OpenAI",
      "required": false,
      "check": "codex --version",
      "signIn": "codex login",
      "role": "Optional. Winskel can give work to Codex models when Codex is installed and signed in.",
      "source": "https://www.winskel.com/docs/connect-codex"
    }
  ],
  "singleProvider": {
    "claudeCodeOnly": {
      "supported": true,
      "answer": "With Claude Code only: yes. Winskel works with Claude Code alone and uses only Claude Code models."
    },
    "codexOnly": {
      "supported": false,
      "answer": "With Codex only: no. A Mac with Codex but no Claude Code cannot start work, because Winskel plans every objective with Claude Code."
    }
  },
  "modes": [
    {
      "name": "Autopilot",
      "summary": "Winskel makes the orchestration decisions. Nothing to configure.",
      "status": "available",
      "statusLabel": "Available now"
    },
    {
      "name": "Preferences",
      "summary": "Winskel still decides, inside boundaries the user sets: allowed and excluded models, preferred models by kind of work, and a priority.",
      "status": "available",
      "statusLabel": "Available now"
    },
    {
      "name": "Custom",
      "summary": "The user sets the implementation, review, and approval rules Winskel follows. Winskel still plans the steps and dependencies.",
      "status": "available",
      "statusLabel": "Available now"
    }
  ],
  "capabilities": [
    {
      "id": "autopilot",
      "name": "Autopilot",
      "status": "available",
      "statusLabel": "Available now",
      "summary": "The default. Give one objective and Winskel decides whether one model owns it or it becomes connected steps, what runs at the same time, and which model does each part.",
      "limitation": "Usually one strong model owns the whole objective. Winskel plans a split when the work is high risk or too large, when a step needs recovery, or when the user asks.",
      "source": "https://www.winskel.com/product/orchestration"
    },
    {
      "id": "nameModel",
      "name": "Name a model or agent system",
      "status": "available",
      "statusLabel": "Available now",
      "summary": "A model or agent system named in the objective is used for that work. Retries and escalation never replace it. If it cannot run, Winskel stops and explains instead of substituting another.",
      "limitation": null,
      "source": "https://www.winskel.com/docs/choosing-models"
    },
    {
      "id": "parallel",
      "name": "Parallel work in Git worktrees",
      "status": "available",
      "statusLabel": "Available now",
      "summary": "Independent parts run at the same time, each in its own Git worktree and branch.",
      "limitation": "A worktree separates Git working state. It is not an operating system sandbox.",
      "source": "https://www.winskel.com/product/parallel"
    },
    {
      "id": "dependencies",
      "name": "Dependencies",
      "status": "available",
      "statusLabel": "Available now",
      "summary": "A step that depends on another waits until the steps it needs have finished and passed their observed checks.",
      "limitation": null,
      "source": "https://www.winskel.com/docs/decomposition"
    },
    {
      "id": "needsYou",
      "name": "Needs You",
      "status": "available",
      "statusLabel": "Available now",
      "summary": "Questions, permission requests, and decisions that need a person appear in one place.",
      "limitation": "Claude Code and Codex expose different question and permission capabilities. System failures show as Failed, not as Needs You.",
      "source": "https://www.winskel.com/docs/needs-you"
    },
    {
      "id": "review",
      "name": "Review",
      "status": "available",
      "statusLabel": "Available now",
      "summary": "One review shows changed files, the step and model that changed them, the diff, and the checks Winskel observed.",
      "limitation": null,
      "source": "https://www.winskel.com/docs/review-verification"
    },
    {
      "id": "observedChecks",
      "name": "Observed checks",
      "status": "available",
      "statusLabel": "Available now",
      "summary": "A check counts as Passed or Failed only when Winskel has the command and its result for that run. Everything else is Not verified.",
      "limitation": "Codex runs its commands inside Codex's own sandbox, where Winskel does not run project checks, so Codex steps show as Not verified unless Codex reported a check it ran.",
      "source": "https://www.winskel.com/docs/review-verification"
    },
    {
      "id": "approve",
      "name": "Approve and Request changes",
      "status": "available",
      "statusLabel": "Available now",
      "summary": "Approve records that the user accepts the result. Request changes sends a follow-up objective.",
      "limitation": "Approve does not merge, push, copy, or delete anything.",
      "source": "https://www.winskel.com/docs/review-verification#decision"
    },
    {
      "id": "permissionModes",
      "name": "Agent permission modes",
      "status": "available",
      "statusLabel": "Available now",
      "summary": "Ask Me, Smart Auto (the default), and Autonomous decide which commands and edits an agent may run without asking.",
      "limitation": "Some actions are blocked in every mode. Agents still run under the user's macOS account.",
      "source": "https://www.winskel.com/docs/permission-modes"
    },
    {
      "id": "routingReason",
      "name": "Routing reason",
      "status": "available",
      "statusLabel": "Available now",
      "summary": "The model chosen for the work and a one-line reason are shown when the work starts.",
      "limitation": null,
      "source": "https://www.winskel.com/docs/model-routing"
    },
    {
      "id": "github",
      "name": "GitHub",
      "status": "available",
      "statusLabel": "Available now",
      "summary": "Optional. Clone a repository from GitHub and open pull requests from Winskel.",
      "limitation": null,
      "source": "https://www.winskel.com/docs/projects-worktrees"
    },
    {
      "id": "preferences",
      "name": "Preferences",
      "status": "available",
      "statusLabel": "Available now",
      "summary": "Model pools, excluded models, preferred models by kind of work, and a quality, speed, cost, or balanced priority. Winskel decides inside them.",
      "limitation": null,
      "source": "https://www.winskel.com/docs/choosing-models#preferences"
    },
    {
      "id": "custom",
      "name": "Custom orchestration",
      "status": "available",
      "statusLabel": "Available now",
      "summary": "The user sets the implementer, reviewer, review rules, failure handling, and approval gates. Winskel still plans the steps. Custom does not set step order, dependencies, parallelism, or a number of repair rounds.",
      "limitation": null,
      "source": "https://www.winskel.com/docs/choosing-models#custom"
    },
    {
      "id": "workflowImport",
      "name": "Workflow file import",
      "status": "available",
      "statusLabel": "Available now",
      "summary": "Import a workflow file for Custom orchestration. Free text becomes planning guidance, never a routing rule.",
      "limitation": null,
      "source": "https://www.winskel.com/product/orchestration"
    },
    {
      "id": "routingHistory",
      "name": "Routing history",
      "status": "available",
      "statusLabel": "Available now",
      "summary": "A full record of which model handled which work, why, and what happened next.",
      "limitation": null,
      "source": "https://www.winskel.com/product/evidence"
    },
    {
      "id": "applyUndo",
      "name": "Apply to project and Undo apply",
      "status": "next_release",
      "statusLabel": "Next release: built and in testing, not in the current public download",
      "summary": "Add a result to the project folder from Winskel, and take it back out.",
      "limitation": null,
      "source": "https://www.winskel.com/product/parallel"
    },
    {
      "id": "plainFolder",
      "name": "Git setup for a plain folder",
      "status": "next_release",
      "statusLabel": "Next release: built and in testing, not in the current public download",
      "summary": "Start a project from a folder that is not yet a Git repository.",
      "limitation": null,
      "source": "https://www.winskel.com/docs/projects-worktrees"
    },
    {
      "id": "planLimits",
      "name": "Free plan limits and Pro checkout",
      "status": "available",
      "statusLabel": "Available now",
      "summary": "Free limits are enforced, and Pro checkout starts in the Winskel app at Settings → Billing.",
      "limitation": null,
      "source": "https://www.winskel.com/pricing"
    },
    {
      "id": "routingLearning",
      "name": "Routing that learns from outcomes",
      "status": "not_available",
      "statusLabel": "Not available",
      "summary": "Routing follows a fixed, versioned policy. It does not learn from the user's code, history, reviews, or ratings today.",
      "limitation": null,
      "source": "https://www.winskel.com/docs/model-routing#learning"
    },
    {
      "id": "cloud",
      "name": "Winskel Cloud",
      "status": "not_available",
      "statusLabel": "Not available",
      "summary": "Not part of the current product.",
      "limitation": null,
      "source": "https://www.winskel.com/docs/known-limitations"
    },
    {
      "id": "phoneControl",
      "name": "Remote phone control",
      "status": "not_available",
      "statusLabel": "Not available",
      "summary": "Not part of the current product.",
      "limitation": null,
      "source": "https://www.winskel.com/docs/known-limitations"
    }
  ],
  "models": {
    "checked": "2026-10-05",
    "claudeCode": [
      {
        "label": "Fable 5.1",
        "id": "claude-fable-5-1"
      },
      {
        "label": "Fable 5",
        "id": "claude-fable-5"
      },
      {
        "label": "Opus 5",
        "id": "claude-opus-5"
      },
      {
        "label": "Opus 5.5",
        "id": "claude-opus-5-5"
      },
      {
        "label": "Sonnet 5",
        "id": "claude-sonnet-5"
      },
      {
        "label": "Sonnet 5.5",
        "id": "claude-sonnet-5-5"
      }
    ],
    "codex": [
      {
        "label": "GPT-6 Astra",
        "id": "gpt-6-astra"
      },
      {
        "label": "GPT-5.6 Sol",
        "id": "gpt-5.6-sol"
      },
      {
        "label": "GPT-5.6 Terra",
        "id": "gpt-5.6-terra"
      },
      {
        "label": "GPT-6.1 Sol",
        "id": "gpt-6.1-sol"
      },
      {
        "label": "GPT-6 Sol",
        "id": "gpt-6-sol"
      }
    ],
    "autopilotDefaults": [
      "Sonnet 5.5",
      "Opus 5.5",
      "GPT-5.6 Sol"
    ],
    "autopilotDefaultsNote": "Winskel tries these in order and uses the first one the user's Mac can run, unless the work calls for something else or the user names a model.",
    "notSupportedAsWorkers": [
      "Cursor",
      "Gemini",
      "Grok",
      "Copilot",
      "OpenCode"
    ],
    "eligibility": "A model is used only when Winskel supports it, the installed Claude Code or Codex reports it can run it, and the user's provider account allows it. A Mac can show fewer models than this list.",
    "source": "https://www.winskel.com/models"
  },
  "pricing": {
    "currency": "USD",
    "plans": [
      {
        "name": "Winskel Free",
        "priceUsdPerMonth": 0,
        "limits": {
          "activeProjects": 5,
          "activeRoutingModels": 5,
          "routesPerMonth": 150
        },
        "availableToUse": true,
        "purchasable": false,
        "note": "No payment. Downloading Winskel and signing in uses Free."
      },
      {
        "name": "Winskel Pro",
        "priceUsdPerMonth": 19,
        "limits": {
          "activeProjects": null,
          "activeRoutingModels": null,
          "routesPerMonth": null
        },
        "availableToUse": true,
        "purchasable": true,
        "note": "Upgrade inside the Winskel app at Settings → Billing. The website does not sell Pro directly."
      }
    ],
    "limitsEnforced": true,
    "proPrice": "$19 a month",
    "limitsNote": "Free limits are enforced. Winskel warns at 120 and 140 routes in a month; route 150 succeeds, and the next route waits until the monthly allowance resets or the user upgrades. Running work continues. Pro checkout starts in the Winskel app at Settings → Billing.",
    "route": "A route is one executable mission Winskel sends to a coding model. Planning and Winskel's own retries on the same model do not use additional routes; a rerun the user starts is new work.",
    "activeRoutingModels": "Winskel detects and shows every supported model. On Free, up to 5 are active in your routing pool at one time.",
    "providerCosts": "Winskel's price does not include Claude Code or Codex. Anthropic and OpenAI subscriptions, usage limits, and charges are separate and still apply.",
    "source": "https://www.winskel.com/pricing"
  },
  "dataHandling": {
    "runsOn": "Claude Code and Codex run on the user's Mac, under the user's macOS account and provider accounts.",
    "leavesTheMac": [
      "Claude Code and Codex send prompts, repository content, and other task information to Anthropic and OpenAI under the user's own agreements with them.",
      "Winskel's hosted service stores the records it needs to coordinate and explain work.",
      "Google sign in shares the user's name, email address, and profile picture with Winskel."
    ],
    "storedByWinskel": "Email, project names and paths, objective and chat text, plans and answers, notes, question and permission text, run status, bounded run events (agent messages, command lines, and short tool output excerpts, which can include code an agent read), summaries, changed file paths and line counts, branch names and commits, attachment names and paths, verification evidence, routing decisions, and provider usage readings.",
    "notStored": "Repository files, patches, and attachment files are read from the Mac and are not stored by Winskel; only the short excerpts in run records can contain code. Winskel does not collect or store Claude Code or Codex credentials.",
    "caution": "Local execution does not mean nothing leaves the Mac. Records and short excerpts can contain source code, paths, command output, or secrets.",
    "website": "The public website uses no advertising trackers or third-party cookies. It uses Vercel Web Analytics to count anonymous page views in aggregate, and Vercel processes normal request information to deliver the site.",
    "sources": [
      "https://www.winskel.com/docs/local-execution",
      "https://www.winskel.com/privacy",
      "https://www.winskel.com/security"
    ]
  },
  "security": [
    "Winskel starts work only in repositories the user explicitly adds and trusts.",
    "Agent permission modes (Ask Me, Smart Auto, Autonomous) control which commands and edits an agent may run without asking. Some actions, such as sudo, git reset --hard, force push, and paths outside the trusted worktree, are blocked in every mode. These are permission rules Winskel applies to agent requests, not operating system enforcement.",
    "Agents run under the user's macOS account. Git worktrees separate working state but are not an operating system sandbox.",
    "Approve a first launch only for a build downloaded from winskel.com."
  ],
  "limitations": [
    "The build is not signed with an Apple Developer ID and is not notarized by Apple. macOS asks the user to approve the first launch.",
    "Apple Silicon Macs with macOS 12 or later only. No Intel Macs, Windows, or Linux.",
    "No automatic updates. New builds come from winskel.com.",
    "Some screens in the app say Alpha. They belong to the same public build.",
    "Claude Code is required. Codex is optional.",
    "Free limits are enforced. Winskel warns at 120 and 140 routes in a month; route 150 succeeds, and the next route waits until the monthly allowance resets or the user upgrades. Running work continues. Pro checkout starts in the Winskel app at Settings → Billing.",
    "Routing does not learn from the user's feedback or history yet.",
    "A numbered list in an objective runs as one step unless the user asks for separate or parallel steps.",
    "Codex steps show as Not verified unless Codex reported a check it ran.",
    "Revert, which adds an inverse commit for one objective's result when Winskel can prove it is safe, is in testing.",
    "Provider usage readings update only when that agent runs and can be stale.",
    "Winskel Cloud and remote phone control are not available.",
    "Provider limits and model availability still apply.",
    "Git worktrees are not a filesystem sandbox."
  ],
  "principle": [
    "The goal is not more agents; it is the smallest team that can finish the objective.",
    "There are three levels of control: Autopilot, Preferences, and Custom orchestration. Explicit developer constraints always win over automatic routing.",
    "Winskel prefers to keep one model on a mission unless specialization, independent review, availability, or escalation justifies a switch.",
    "Escalation is bounded: when a mission's checks fail, the same model gets one repair turn, then the mission moves once to a stronger model. If that also fails, the objective stops as Failed with the reason."
  ],
  "evidenceGuide": [
    {
      "kind": "Current capabilities",
      "text": "What the current public download does today. This reference marks each one as available."
    },
    {
      "kind": "Next release",
      "text": "Built and in testing in the release candidate, not in the public download yet. Screenshots of these features are captures of the release candidate."
    },
    {
      "kind": "Workflow illustrations",
      "text": "Diagrams labeled as illustrations, built from Winskel's example project. They explain the workflow; they are not recorded runs and contain no measured times, token counts, costs, or percentages."
    },
    {
      "kind": "Winskel Lab method and design",
      "text": "The Winskel Lab page (https://www.winskel.com/lab) explains how Winskel intends to compare models and workflows. Its workflow explorer, quality and cost diagram, and experiment matrix are conceptual and labeled as such: they contain no data points, scores, costs, or percentages, and each matrix cell is a proposed comparison."
    },
    {
      "kind": "Measured comparisons",
      "text": "None are published yet. Winskel does not currently claim a measured speedup, a token saving, or a quality improvement."
    },
    {
      "kind": "Research questions",
      "text": "Open questions on the Winskel Lab page, such as when a second model reviewing the work catches problems that a second pass by the same model misses. They are not findings."
    },
    {
      "kind": "Long-term vision",
      "text": "Winskel intends to study research and data analysis workflows. No product for those fields exists or is available, and no launch date is set. These are directions, not products."
    }
  ],
  "research": {
    "name": "Winskel Lab",
    "page": "https://www.winskel.com/lab",
    "summary": "Winskel Lab is Winskel's research program for comparing AI models alone and in workflows on specific tasks, starting with coding.",
    "purpose": "Compare individual models and model workflows on specific tasks, to find when a combination improves the result, when it reaches comparable quality at lower cost, and when one model is enough.",
    "currentFocus": "Coding.",
    "futureDirections": [
      "Research workflows",
      "Data analysis workflows"
    ],
    "futureDirectionsNote": "Directions to study later, not products. No launch date is set.",
    "method": "Whole configurations are compared (model version, role, tools, context, settings, retries, verification and workflow) under equal conditions, against a well configured single model, with independent evaluation and confirmation on separate tasks. Failures stay in the denominator, and unknown values are reported as unknown, never as zero.",
    "plannedCoverage": "Winskel aims to evaluate models from multiple providers. Planned coverage is not evaluated coverage.",
    "evaluatedCoverage": "None published. Winskel does not claim a count of evaluated models or providers.",
    "findings": [],
    "productBoundary": "Lab research is separate from the product. A model evaluated in the Lab is not thereby supported by the product, and Lab results do not change the product automatically: routing follows a fixed, versioned policy, and learning from routing outcomes is not available."
  },
  "thingsToKnow": [
    {
      "id": "independent",
      "question": "Is Winskel partnered with Anthropic or OpenAI?",
      "answer": "No. Winskel is an independent product. It is not made by, partnered with, or endorsed by Anthropic or OpenAI.",
      "url": "https://www.winskel.com/#independent"
    },
    {
      "id": "code-and-privacy",
      "question": "Does my code stay entirely on my Mac?",
      "answer": "No. Claude Code and Codex send relevant code and context to Anthropic and OpenAI as part of their normal operation. Winskel's own storage is separate: Winskel does not store your repository's files or patches, which the app reads from your Mac when you open them. Winskel does keep the records it needs to coordinate work, including objective text, file paths, and short excerpts of agent activity that can include code. The Privacy page explains what Winskel collects.",
      "url": "https://www.winskel.com/#code-and-privacy"
    },
    {
      "id": "routing-learning",
      "question": "Does routing get smarter as more people use Winskel?",
      "answer": "Not today. Winskel records which model it chose and why, but learning from outcomes is still in development. Routing follows a fixed, versioned policy, and outcomes from other developers do not currently influence your routing.",
      "url": "https://www.winskel.com/#routing-learning"
    },
    {
      "id": "performance",
      "question": "Is Winskel faster or more efficient with tokens?",
      "answer": "Winskel does not currently claim a measured speedup or a token savings percentage. Any performance claim needs published benchmark results and a clear explanation of what was measured.",
      "url": "https://www.winskel.com/#performance"
    },
    {
      "id": "working-copies",
      "question": "Do agents edit the same working copy?",
      "answer": "No. Independent missions run in separate Git worktrees, each with its own working files and branch. Their changes still need to be integrated and reviewed, and separate working copies do not guarantee that changes never conflict. A worktree is not a security sandbox. See parallel work.",
      "url": "https://www.winskel.com/#working-copies"
    },
    {
      "id": "multiple-models",
      "question": "Does Winskel always use multiple models?",
      "answer": "No. Most objectives stay with one model. Winskel divides suitable work into separate missions when it helps, and several missions can run on the same model, so more agents working does not necessarily mean more models. See orchestration.",
      "url": "https://www.winskel.com/#multiple-models"
    }
  ],
  "glossary": [
    {
      "term": "Objective",
      "definition": "The outcome the user asks for in one message, and the record of what happened to it."
    },
    {
      "term": "Mission",
      "definition": "One unit of work within an objective, given to one agent and one model. Most objectives are one mission. The app also calls a mission a step."
    },
    {
      "term": "Agent",
      "definition": "A coding agent tool Winskel runs on the Mac: Claude Code or Codex."
    },
    {
      "term": "Model",
      "definition": "The language model an agent runs for a mission, such as Sonnet 5.5 or GPT-5.6 Sol."
    },
    {
      "term": "Provider or harness",
      "definition": "The agent system and the company behind it: Claude Code from Anthropic, or Codex from OpenAI. Winskel uses the user's own installation and account."
    },
    {
      "term": "Working copy",
      "definition": "The separate Git worktree each run gets, on its mission's own branch, so concurrent work never shares one directory."
    },
    {
      "term": "Route",
      "definition": "A route is one executable mission Winskel sends to a coding model. It is also the unit the Free plan counts."
    },
    {
      "term": "Review",
      "definition": "Where the user inspects the result: changed files, the step and model behind them, diffs, observed checks, and the decision to Approve or Request changes."
    },
    {
      "term": "Apply",
      "definition": "Adding a result to the project folder from Winskel (Apply to project) and taking it back out (Undo apply). Next release: built and in testing, not in the current public download. In the current public build the result stays on its own Git branch, and the user brings it into the project with Git or a pull request."
    },
    {
      "term": "Verification",
      "definition": "The evidence that a check ran: Passed or Failed only when Winskel has the command and its result. Not verified means Winskel did not receive sufficient evidence that a check ran. An objective as a whole is never labeled verified."
    },
    {
      "term": "Needs You",
      "definition": "The list of questions, permission requests, and decisions that need the user. A system failure is shown as Failed, not as Needs You."
    }
  ],
  "documentation": [
    {
      "title": "Install Winskel",
      "page": "https://www.winskel.com/docs/install",
      "markdown": "https://www.winskel.com/agents/docs/install.md",
      "updated": "2026-10-06"
    },
    {
      "title": "Connect Claude Code",
      "page": "https://www.winskel.com/docs/connect-claude-code",
      "markdown": "https://www.winskel.com/agents/docs/connect-claude-code.md",
      "updated": "2026-10-06"
    },
    {
      "title": "Connect Codex",
      "page": "https://www.winskel.com/docs/connect-codex",
      "markdown": "https://www.winskel.com/agents/docs/connect-codex.md",
      "updated": "2026-10-06"
    },
    {
      "title": "Your first objective",
      "page": "https://www.winskel.com/docs/first-objective",
      "markdown": "https://www.winskel.com/agents/docs/first-objective.md",
      "updated": "2026-10-06"
    },
    {
      "title": "Choosing models",
      "page": "https://www.winskel.com/docs/choosing-models",
      "markdown": "https://www.winskel.com/agents/docs/choosing-models.md",
      "updated": "2026-10-06"
    },
    {
      "title": "Model routing",
      "page": "https://www.winskel.com/docs/model-routing",
      "markdown": "https://www.winskel.com/agents/docs/model-routing.md",
      "updated": "2026-10-06"
    },
    {
      "title": "How Winskel breaks down work",
      "page": "https://www.winskel.com/docs/decomposition",
      "markdown": "https://www.winskel.com/agents/docs/decomposition.md",
      "updated": "2026-10-06"
    },
    {
      "title": "Projects and worktrees",
      "page": "https://www.winskel.com/docs/projects-worktrees",
      "markdown": "https://www.winskel.com/agents/docs/projects-worktrees.md",
      "updated": "2026-10-06"
    },
    {
      "title": "Needs You",
      "page": "https://www.winskel.com/docs/needs-you",
      "markdown": "https://www.winskel.com/agents/docs/needs-you.md",
      "updated": "2026-10-06"
    },
    {
      "title": "Review and verification",
      "page": "https://www.winskel.com/docs/review-verification",
      "markdown": "https://www.winskel.com/agents/docs/review-verification.md",
      "updated": "2026-10-06"
    },
    {
      "title": "Permission modes",
      "page": "https://www.winskel.com/docs/permission-modes",
      "markdown": "https://www.winskel.com/agents/docs/permission-modes.md",
      "updated": "2026-10-06"
    },
    {
      "title": "Local execution",
      "page": "https://www.winskel.com/docs/local-execution",
      "markdown": "https://www.winskel.com/agents/docs/local-execution.md",
      "updated": "2026-10-06"
    },
    {
      "title": "Supported models",
      "page": "https://www.winskel.com/docs/supported-models",
      "markdown": "https://www.winskel.com/agents/docs/supported-models.md",
      "updated": "2026-10-06"
    },
    {
      "title": "Known limitations",
      "page": "https://www.winskel.com/docs/known-limitations",
      "markdown": "https://www.winskel.com/agents/docs/known-limitations.md",
      "updated": "2026-10-06"
    }
  ],
  "unknowns": [
    {
      "topic": "New account sign ups",
      "status": "not_confirmed",
      "note": "Sign in uses Google. Whether anyone can create an account today, or only invited users, was not confirmed in this review."
    }
  ],
  "support": {
    "email": "ahmed@winskel.com",
    "contact": "https://www.winskel.com/contact",
    "security": "https://www.winskel.com/security"
  }
}