{
  "fixes": {
    "slug": "tasker-ai",
    "name": "Tasker AI",
    "listing": "https://www.anchorterminal.com/tools/tasker-ai",
    "markdown": "# Fix list: Tasker AI\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/tasker-ai, the October 2026 research run, assessed 21 October 2026. Grade F, 7.6 out of 100.\n\nThis is everything the published grade says the listing lacks, the biggest possible gain to the total first. It comes from the reason given for each score, the checklist each category was scored against (https://www.anchorterminal.com/benchmark/#checklist), the provenance checks, the deductions, what we couldn't check and what the review panel asked for. A fix counts at the next check, once it's public.\n\nFor a coding agent working on Tasker AI: work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published.\n\n## 1. Security \u0026 auth, 0 out of 100, up to 17.5 more on the total\n\nWhy it scored 0: Graded on the interface an outside agent can use. The site shows a bearer key in its example call, but no key page or working endpoint was found, so the credential, least-privilege, injection and audit lines score nothing (0 of 30, 0 of 20, 0 of 15, 0 of 15). The security programme line doesn't need an interface and is scored. tasker.ai/.well-known/security.txt returns the HTML shell, so no valid security.txt, and no disclosure policy, bug bounty or advisories were found. DAPI's privacy policy claims encryption, penetration testing, MFA and role-based access, which are claims, as Lobby's were. The only certification in the site's script is SOC-II Type 2 in copy for DAPI's separate settlement product, with no report and nothing tying it to Tasker. The Orchid dossier gave 0 where the SOC 2 it pointed to wasn't its own (0 of 20).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-security):\n\n- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.\n- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.\n- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.\n- 0 to 15, audit logs or per-call visibility for the operator.\n- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.\n\nModels are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing.\n\n## 2. Reliability, 15 out of 100, up to 17 more on the total\n\nWhy it scored 15: Read with the hosted lines. No status page found. status.tasker.ai doesn't resolve, and api.tasker.ai/health answers OK, which isn't a status page (0). No readable incident history (5). No rate or usage limits published in numbers (0). No overload or retry guidance (0). The Enterprise plan lists premium support and an SLA, but no SLA terms are published (0). Every paid plan shows Get started and nothing for Tasker is labelled beta (10).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):\n\nHosted APIs, MCP servers, models and platforms.\n\n- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).\n- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.\n- 15, rate limits documented with numbers.\n- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.\n- 10, an SLA published for any paid tier.\n- 10, the surface agents use is generally available, not beta or preview.\n\nLocal packages, SDKs, frameworks and stdio MCP servers.\n\n- 20, installs from an official package with supported runtimes stated.\n- 25, a public CI and test suite, passing on the default branch.\n- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).\n- 15, semver discipline and breaking changes called out in a changelog.\n- 15, version 1.0 or later, or declared stable.\n\nProtocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors.\n\n## 3. Schema \u0026 documentation, 0 out of 100, up to 16.3 more on the total\n\nWhy it scored 0: Graded on the interface an outside agent can use. The site's Tasker API page says the API covers agents, tasks, integrations and workflows through REST, webhooks and MCP, and shows one curl call to POST api.tasker.ai/v1/tasks. No reference, OpenAPI file, tool list or key page was found, and on 21 October 2026 GET requests to /v1/tasks, /v1, /openapi.json and /mcp on api.tasker.ai answered 404. With nothing to read, we take the reading the 12 and 14 October audits took for listings without an interface, so the contract, description, typed-input and example lines score nothing (0 of 25, 0 of 20, 0 of 15, 0 of 15). tasker.ai/llms.txt returns the site's HTML shell, and no Markdown docs were found (0). Nothing to version (0 of 15).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):\n\nAPIs and MCP servers.\n\n- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).\n- 10, llms.txt or Markdown docs served for agents.\n- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.\n- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.\n- 0 to 15, examples and documented error responses.\n- 15, versioning and a public changelog.\n\nModels are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference.\n\n## 4. Agent ergonomics, 0 out of 100, up to 16.3 more on the total\n\nWhy it scored 0: Graded on the interface an outside agent can use. None could be reached for Tasker, so context cost, pagination, errors, retries and defaults have nothing to score (0 on each line). This says nothing about the product for people.\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):\n\n- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).\n- 20, pagination, filtering and output-size controls.\n- 20, actionable, documented error responses, codes and messages an agent can recover from.\n- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.\n- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.\n\nModels are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs.\n\n## 5. Payments \u0026 pricing, 20 out of 100, up to 10 more on the total\n\nWhy it scored 20: Read with the hosted rule. No x402, MPP or L402 for Tasker. The x402 copy in the same script belongs to DAPI's separate products (0). Plans are public in the site's pricing code, Free at US$0, Starter US$30, Business US$50 and Business Max US$150 a month, 20% off billed annually, and Enterprise on request, with no per-unit price, so plan-only (10). The Free plan is described as build with your own keys, so model use is paid elsewhere, and the card question is unanswered, hedged the way the Screenpipe and OpenInstinct dossiers' were (10 of 20). A person signs up through a Clerk sign-in in a browser (0).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):\n\nThe published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).\n\n- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.\n- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for \"contact sales\" or prices behind a login.\n- 20, a free tier or trial that doesn't need a card.\n- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).\n\nPayment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.\n\nOpen-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol.\n\n## 6. Maintenance \u0026 community, 2 out of 100, up to 8.6 more on the total\n\nWhy it scored 2: Read for a closed service. No dated release, changelog or app-store listing for Tasker found, and the only dates in the script are demo content and the legal documents (0). No dated entries in the last 90 days (0). A contact page, with email support listed only on Business Max, untested, and no changelog (2 of 15). No Tasker MCP server or SDK found, and the create-tasker package the site shows isn't on npm (0). No package or CI to judge (0).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):\n\n- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.\n- 20, at least three releases or dated changelog entries in the last 90 days.\n- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.\n- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).\n- 10, package health, current dependencies and CI.\n\nModels are read for deprecation notice periods and model churn rather than release counts.\n\n## 7. Transparency \u0026 trust, 45 out of 100, up to 4.8 more on the total\n\nMade of editorial 34, provenance 55.\n\nWhy it scored 45: The site says Tasker AI is open source and links github.com/tasker-ai, but GitHub refused our requests with 403, the npm package it names doesn't exist, and no licence was found. So we score the terms we could read, a closed service under DAPI, Inc.'s Master Service Agreement of 21 June 2026, doing business as Tasker AI (15). This line would change if a public repository under an OSI licence is shown. The privacy policy of 30 September 2026 keeps Google Workspace data out of generalised models, uses aggregated and anonymised data to improve services, keeps data as long as reasonably necessary with no periods, and says agents may accept third-party privacy and cookie policies on the user's behalf. The agreement says DAPI staff may view confidential information for debugging. Consistent, with a Google exclusion and retention criteria but no periods, the Wajo reading (12 of 30). The agreement lets DAPI modify or discontinue the service with or without notice but says it will make reasonable efforts to notify users of significant changes, with 30 days' notice of fee changes and no deprecation policy, the Instinct reading (3 of 20). Subprocessors by category, with Stripe and Strac named for card data and no model providers or regions, the Tomo reading (4 of 20).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):\n\n- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.\n- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).\n- 0 to 20, a deprecation policy or notices with dates.\n- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).\n\nThe other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.\n\nProvenance checks not met in full (half of this category, computed from checked facts):\n\n- Domain age: tasker.ai, no registry record we could read (0 of 15)\n- Status page: not found (0 of 10)\n- Changelog: not found (0 of 10)\n- security.txt: not found (0 of 10)\n\n## Deductions\n\nEach comes off the total. A fixed and documented problem counts for less at the next check.\n\n- Misleading claim (-2), read on 21 October 2026. The Tasker API page (route /tasker-api, enabled under Developer in Tasker's navigation, given a Tasker AI page title in the script tasker.ai serves) tells developers to run npx create-tasker@latest and calls Tasker open source. The npm registry answered 404 for create-tasker on 21 October 2026, so the advertised install command fails, and anyone who registers the name could take it. Precedent is Gumloop's -2 for SDK coverage its docs don't bear out. Sources https://tasker.ai/assets/index-on3HrOEj.js and https://registry.npmjs.org/create-tasker/latest (both read by us on 21 October 2026).\n\n## What we couldn't check\n\nWhat we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it.\n\n- unchecked: github.com/tasker-ai. GitHub answered 403, including to robots.txt, so whether a public repository and licence exist wasn't established. Couldn't check is not absent, and the licence and maintenance lines would change if one exists.\n- unchecked: whether POST /v1/tasks exists for keyed customers. Only GET requests were made, and a POST-only route would also answer 404 to a GET.\n- Which pages the live site renders beyond the routes enabled in its navigation wasn't established, because tasker.ai is drawn by script and the bundle also holds pages for DAPI's separate products.\n- Whether the Free plan takes a card wasn't established. No account was created.\n- No mobile app listing was found for the desktop and mobile apps the site names.\n\n## Weaknesses\n\n- The REST API, webhooks and MCP the site names have no public documentation, and the paths tried on api.tasker.ai answered 404.\n- npx create-tasker@latest is advertised, but no create-tasker package was on npm on 21 October 2026.\n- No status page, changelog or valid security.txt.\n- The privacy policy lets agents accept third-party privacy and cookie policies on the user's behalf.\n\n## What costs an agent a turn today\n\nThe notes we give agents before they call it. Each one is a workaround an agent shouldn't need.\n\n- Don't plan to call Tasker from another agent until it publishes API documentation. GET api.tasker.ai/v1/tasks returned 404.\n- Don't run npx create-tasker@latest. No package by that name was on npm on 21 October 2026, so anyone could register it.\n- Tell the owner that the Free plan needs their own model API keys, billed by those providers.\n\n## What the review panel asked for\n\n- published API docs and key page\n- publish or remove create-tasker\n- a dated changelog\n- published API documentation\n- document API pricing\n- register or remove create-tasker\n- publish key scopes\n\n## When it's done\n\nSend what changed and where it's published as a dispute (https://www.anchorterminal.com/builders/#disputes, or `POST https://www.anchorterminal.com/api/v1/contact` with `\"kind\": \"dispute\"`). Disputes are answered in public, and the listing is checked again by the same checklist. Paying for an audit or a listing claim changes nothing here.\n",
    "grade": "F",
    "score": 7.6,
    "assessed": "2026-10-21",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "security",
        "name": "Security \u0026 auth",
        "score": 0,
        "maxGain": 17.5,
        "reason": "Graded on the interface an outside agent can use. The site shows a bearer key in its example call, but no key page or working endpoint was found, so the credential, least-privilege, injection and audit lines score nothing (0 of 30, 0 of 20, 0 of 15, 0 of 15). The security programme line doesn't need an interface and is scored. tasker.ai/.well-known/security.txt returns the HTML shell, so no valid security.txt, and no disclosure policy, bug bounty or advisories were found. DAPI's privacy policy claims encryption, penetration testing, MFA and role-based access, which are claims, as Lobby's were. The only certification in the site's script is SOC-II Type 2 in copy for DAPI's separate settlement product, with no report and nothing tying it to Tasker. The Orchid dossier gave 0 where the SOC 2 it pointed to wasn't its own (0 of 20).",
        "checklist": [
          "- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.\n- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.\n- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.\n- 0 to 15, audit logs or per-call visibility for the operator.\n- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.",
          "Models are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-security"
      },
      {
        "key": "reliability",
        "name": "Reliability",
        "score": 15,
        "maxGain": 17,
        "reason": "Read with the hosted lines. No status page found. status.tasker.ai doesn't resolve, and api.tasker.ai/health answers OK, which isn't a status page (0). No readable incident history (5). No rate or usage limits published in numbers (0). No overload or retry guidance (0). The Enterprise plan lists premium support and an SLA, but no SLA terms are published (0). Every paid plan shows Get started and nothing for Tasker is labelled beta (10).",
        "checklist": [
          "Hosted APIs, MCP servers, models and platforms.",
          "- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).\n- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.\n- 15, rate limits documented with numbers.\n- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.\n- 10, an SLA published for any paid tier.\n- 10, the surface agents use is generally available, not beta or preview.",
          "Local packages, SDKs, frameworks and stdio MCP servers.",
          "- 20, installs from an official package with supported runtimes stated.\n- 25, a public CI and test suite, passing on the default branch.\n- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).\n- 15, semver discipline and breaking changes called out in a changelog.\n- 15, version 1.0 or later, or declared stable.",
          "Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-reliability"
      },
      {
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "score": 0,
        "maxGain": 16.3,
        "reason": "Graded on the interface an outside agent can use. The site's Tasker API page says the API covers agents, tasks, integrations and workflows through REST, webhooks and MCP, and shows one curl call to POST api.tasker.ai/v1/tasks. No reference, OpenAPI file, tool list or key page was found, and on 21 October 2026 GET requests to /v1/tasks, /v1, /openapi.json and /mcp on api.tasker.ai answered 404. With nothing to read, we take the reading the 12 and 14 October audits took for listings without an interface, so the contract, description, typed-input and example lines score nothing (0 of 25, 0 of 20, 0 of 15, 0 of 15). tasker.ai/llms.txt returns the site's HTML shell, and no Markdown docs were found (0). Nothing to version (0 of 15).",
        "checklist": [
          "APIs and MCP servers.",
          "- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).\n- 10, llms.txt or Markdown docs served for agents.\n- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.\n- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.\n- 0 to 15, examples and documented error responses.\n- 15, versioning and a public changelog.",
          "Models are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-schema"
      },
      {
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "score": 0,
        "maxGain": 16.3,
        "reason": "Graded on the interface an outside agent can use. None could be reached for Tasker, so context cost, pagination, errors, retries and defaults have nothing to score (0 on each line). This says nothing about the product for people.",
        "checklist": [
          "- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).\n- 20, pagination, filtering and output-size controls.\n- 20, actionable, documented error responses, codes and messages an agent can recover from.\n- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.\n- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.",
          "Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-ergonomics"
      },
      {
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "score": 20,
        "maxGain": 10,
        "reason": "Read with the hosted rule. No x402, MPP or L402 for Tasker. The x402 copy in the same script belongs to DAPI's separate products (0). Plans are public in the site's pricing code, Free at US$0, Starter US$30, Business US$50 and Business Max US$150 a month, 20% off billed annually, and Enterprise on request, with no per-unit price, so plan-only (10). The Free plan is described as build with your own keys, so model use is paid elsewhere, and the card question is unanswered, hedged the way the Screenpipe and OpenInstinct dossiers' were (10 of 20). A person signs up through a Clerk sign-in in a browser (0).",
        "checklist": [
          "The published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).",
          "- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.\n- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for \"contact sales\" or prices behind a login.\n- 20, a free tier or trial that doesn't need a card.\n- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).",
          "Payment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.",
          "Open-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-payments"
      },
      {
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "score": 2,
        "maxGain": 8.6,
        "reason": "Read for a closed service. No dated release, changelog or app-store listing for Tasker found, and the only dates in the script are demo content and the legal documents (0). No dated entries in the last 90 days (0). A contact page, with email support listed only on Business Max, untested, and no changelog (2 of 15). No Tasker MCP server or SDK found, and the create-tasker package the site shows isn't on npm (0). No package or CI to judge (0).",
        "checklist": [
          "- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.\n- 20, at least three releases or dated changelog entries in the last 90 days.\n- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.\n- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).\n- 10, package health, current dependencies and CI.",
          "Models are read for deprecation notice periods and model churn rather than release counts."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-maintenance"
      },
      {
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "score": 45,
        "maxGain": 4.8,
        "reason": "The site says Tasker AI is open source and links github.com/tasker-ai, but GitHub refused our requests with 403, the npm package it names doesn't exist, and no licence was found. So we score the terms we could read, a closed service under DAPI, Inc.'s Master Service Agreement of 21 June 2026, doing business as Tasker AI (15). This line would change if a public repository under an OSI licence is shown. The privacy policy of 30 September 2026 keeps Google Workspace data out of generalised models, uses aggregated and anonymised data to improve services, keeps data as long as reasonably necessary with no periods, and says agents may accept third-party privacy and cookie policies on the user's behalf. The agreement says DAPI staff may view confidential information for debugging. Consistent, with a Google exclusion and retention criteria but no periods, the Wajo reading (12 of 30). The agreement lets DAPI modify or discontinue the service with or without notice but says it will make reasonable efforts to notify users of significant changes, with 30 days' notice of fee changes and no deprecation policy, the Instinct reading (3 of 20). Subprocessors by category, with Stripe and Strac named for card data and no model providers or regions, the Tomo reading (4 of 20).",
        "blend": "editorial 34, provenance 55",
        "checklist": [
          "- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.\n- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).\n- 0 to 20, a deprecation policy or notices with dates.\n- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).",
          "The other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-transparency"
      }
    ],
    "provenance": [
      {
        "label": "Domain age",
        "value": "tasker.ai, no registry record we could read",
        "points": 0,
        "max": 15
      },
      {
        "label": "Status page",
        "value": "not found",
        "points": 0,
        "max": 10
      },
      {
        "label": "Changelog",
        "value": "not found",
        "points": 0,
        "max": 10
      },
      {
        "label": "security.txt",
        "value": "not found",
        "points": 0,
        "max": 10
      }
    ],
    "deductions": [
      "Misleading claim (-2), read on 21 October 2026. The Tasker API page (route /tasker-api, enabled under Developer in Tasker's navigation, given a Tasker AI page title in the script tasker.ai serves) tells developers to run npx create-tasker@latest and calls Tasker open source. The npm registry answered 404 for create-tasker on 21 October 2026, so the advertised install command fails, and anyone who registers the name could take it. Precedent is Gumloop's -2 for SDK coverage its docs don't bear out. Sources https://tasker.ai/assets/index-on3HrOEj.js and https://registry.npmjs.org/create-tasker/latest (both read by us on 21 October 2026)."
    ],
    "unchecked": [
      "unchecked: github.com/tasker-ai. GitHub answered 403, including to robots.txt, so whether a public repository and licence exist wasn't established. Couldn't check is not absent, and the licence and maintenance lines would change if one exists.",
      "unchecked: whether POST /v1/tasks exists for keyed customers. Only GET requests were made, and a POST-only route would also answer 404 to a GET.",
      "Which pages the live site renders beyond the routes enabled in its navigation wasn't established, because tasker.ai is drawn by script and the bundle also holds pages for DAPI's separate products.",
      "Whether the Free plan takes a card wasn't established. No account was created.",
      "No mobile app listing was found for the desktop and mobile apps the site names."
    ],
    "weaknesses": [
      "The REST API, webhooks and MCP the site names have no public documentation, and the paths tried on api.tasker.ai answered 404.",
      "npx create-tasker@latest is advertised, but no create-tasker package was on npm on 21 October 2026.",
      "No status page, changelog or valid security.txt.",
      "The privacy policy lets agents accept third-party privacy and cookie policies on the user's behalf."
    ],
    "agentNotes": [
      "Don't plan to call Tasker from another agent until it publishes API documentation. GET api.tasker.ai/v1/tasks returned 404.",
      "Don't run npx create-tasker@latest. No package by that name was on npm on 21 October 2026, so anyone could register it.",
      "Tell the owner that the Free plan needs their own model API keys, billed by those providers."
    ],
    "requests": [
      {
        "text": "published API docs and key page",
        "reviews": 1
      },
      {
        "text": "publish or remove create-tasker",
        "reviews": 1
      },
      {
        "text": "a dated changelog",
        "reviews": 1
      },
      {
        "text": "published API documentation",
        "reviews": 1
      },
      {
        "text": "document API pricing",
        "reviews": 1
      },
      {
        "text": "register or remove create-tasker",
        "reviews": 1
      },
      {
        "text": "publish key scopes",
        "reviews": 1
      }
    ],
    "recheck": "https://www.anchorterminal.com/builders/#disputes"
  },
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-10-21",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.6",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  }
}