folk

# Fix list: folk

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/folk-nozomio, the October 2026 research run, assessed 14 October 2026. Grade F, 19.8 out of 100.

This 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.

For a coding agent working on folk: 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.

## 1. Security & auth, 3 out of 100, up to 17 more on the total

Why it scored 3: Graded on the interface an outside agent can use. With none for folk, the credential, least-privilege, injection and audit lines score nothing (0 of 30, 0 of 20, 0 of 15, 0 of 15), whatever the service does for its owner. The security programme line doesn't need an interface and is scored. For the record, Google apps can connect read-only, banks connect read-only through Plaid, sensitive iPhone Health, Calendar, Reminder and Contact writes need confirmation, and folk says it never moves money on its own. folk.com/.well-known/security.txt is valid to 13 April 2027 but names only support@nozomio.com, with no disclosure policy, bug bounty, certification or advisories found. That's the Instinct reading for a security.txt with a support address (3 of 20).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-security):

- 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.
- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.
- 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.
- 0 to 15, audit logs or per-call visibility for the operator.
- 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.

## 2. Agent ergonomics, 0 out of 100, up to 16.3 more on the total

Why it scored 0: Graded on the interface an outside agent can use. folk has none, so context cost, pagination, errors, retries and defaults have nothing to score (0 on each line). This says nothing about the service for people.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):

- 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).
- 20, pagination, filtering and output-size controls.
- 20, actionable, documented error responses, codes and messages an agent can recover from.
- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.
- 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.

## 3. Reliability, 25 out of 100, up to 15 more on the total

Why it scored 25: Read with the hosted lines. No status page found. status.folk.com resolves to the marketing site (0). No readable incident history (5). pricing.md, which llms.txt calls the structured pricing for AI agents, sets Free at 10 minutes of calls a week and Pro at 120 minutes a month, with messages unlimited under fair use. llms.txt gives the free tier as 20 messages a day. Numbers are published, the Marmot reading for plan limits, though two of the vendor's files disagree (10 of 15). No overload or retry guidance (0). No SLA (0). folk takes sign-ups, with WhatsApp rolling out by region, and isn't labelled beta (10).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):

Hosted APIs, MCP servers, models and platforms.

- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).
- 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.
- 15, rate limits documented with numbers.
- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.
- 10, an SLA published for any paid tier.
- 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.
- 25, a public CI and test suite, passing on the default branch.
- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).
- 15, semver discipline and breaking changes called out in a changelog.
- 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.

## 4. Schema & documentation, 10 out of 100, up to 14.6 more on the total

Why it scored 10: Graded on the interface an outside agent can use, as GRADER.md asks. folk has no API, MCP server or A2A endpoint for an agent, so the contract, description, typed-input and example lines score nothing (0 of 25, 0 of 20, 0 of 15, 0 of 15). That is a statement about agent access, not about the service for people. llms.txt and a Markdown pricing file served for agents (10). The versioning and changelog line versions an agent interface, and with none there is nothing to version, so it scores nothing (0 of 15), the reading the 12 October audit applied to every listing without an agent interface.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):

APIs and MCP servers.

- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).
- 10, llms.txt or Markdown docs served for agents.
- 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.
- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.
- 0 to 15, examples and documented error responses.
- 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.

## 5. Payments & pricing, 30 out of 100, up to 8.8 more on the total

Why it scored 30: Read with the hosted rule. No x402, MPP or L402 (0). Plans are public, Free, Pro at $9.99 a month or $99.99 a year ($5 a month in many countries) and Max at $99.99 a month on the US App Store per the terms ($100 in llms.txt), with no per-unit price (10). pricing.md says Free is $0 forever with no card (20). A person signs up at folk.com (0).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):

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.
- 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.
- 20, a free tier or trial that doesn't need a card.
- 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.

## 6. Maintenance & community, 35 out of 100, up to 5.7 more on the total

Why it scored 35: Read for a closed service. folk's iOS app, sold by Nozomio Inc. and linking to folk.com, released 1.0.0 on 7 October and 1.1.0 on 12 October 2026 on the App Store (30). Two releases in the last 90 days and no changelog (0 of 20). Descriptive App Store notes and support@nozomio.com, which we didn't test, the reading taken for Caddy (5 of 15). No MCP server or SDK (0). No package or CI to judge (0). llms.txt says there's no app in the App Store, which the listing contradicts.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):

- 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.
- 20, at least three releases or dated changelog entries in the last 90 days.
- 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.
- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).
- 10, package health, current dependencies and CI.

Models are read for deprecation notice periods and model churn rather than release counts.

## 7. Transparency & trust, 67 out of 100, up to 2.9 more on the total

Made of editorial 57, provenance 76.

Why it scored 67: Closed service under terms updated on 8 September 2026 naming Nozomio, Inc. (15). The privacy policy of 8 October 2026 says folk never sells data or uses it to train AI models, model providers are on API terms that bar training, the LLM observability tools (Langfuse, Lemma and Raindrop) see message content only to fix replies, and account deletion removes memories, credentials and companion databases with retries for failed clean-up. Retention otherwise depends on the provider, with no periods (22 of 30). No deprecation policy or notices found (2 of 20). The subprocessor page of 11 October 2026 names each provider with a region (AWS in the United States, Daytona in the United States or EU) (18 of 20).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):

- 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.
- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).
- 0 to 20, a deprecation policy or notices with dates.
- 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.

Provenance checks not met in full (half of this category, computed from checked facts):

- Status page: not found (0 of 10)
- Changelog: not found (0 of 10)

## What we couldn't check

What 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.

- Which free-tier message limit applies, unlimited under fair use (pricing.md) or 20 a day (llms.txt).
- How long data is kept by each provider.

## Weaknesses

- No API, MCP server or A2A endpoint for an outside agent.
- llms.txt gives 20 messages a day and Max at $100, while pricing.md says unlimited messages and the terms say $99.99.
- llms.txt says there's no App Store app, while the App Store lists folk's iOS app since 7 October 2026.
- No status page or changelog found.
- security.txt names only a general support address.

## What costs an agent a turn today

The notes we give agents before they call it. Each one is a workaround an agent shouldn't need.

- Don't plan to call folk from another agent. It answers only the owner's iMessage, Telegram or WhatsApp thread and iPhone app.
- Quote limits and prices from pricing.md and the terms, and note that llms.txt gives different free-tier limits.

## When it's done

Send 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.