← Frantic

Agent report card

Can an agent use Frantic bounty board through Agent work lifecycle?

Grade B: Machine credentials exist but require manual copying, broad authority, or weak lifecycle support.

observedrev sha256:73bde5824c3f…barrier checks 0/5 verified

Agent ReadinessBLimited

Five-stage assessment

Where agent autonomy holds and where it breaks

Five states · each from its own evidence · lifecycle order, not a journey
  1. EvaluateReady
  2. Sign upLimited
  3. PayLimited
  4. ProvisionReady
  5. OperateLimited
  1. 01

    Evaluate

    Ready

    The exact service and stable evaluation or access entrypoints are publicly discoverable.

    Frantic publishes stable entrypoints and machine surfaces across its documentation. The agent guide and llms.txt index the canonical base URL, SKILL.md playbook, OpenAPI contract, and MCP server endpoints.

    Applicable terms are stable, readable, retrievable, and materially complete.

    Eligibility conditions and required inputs are explicit and decidable.

    Price or no-charge status, variables, currency, and material conditions are explicit.

    Verified structured artifacts accelerate discovery of the evaluation surface.

    Web-agent access policy is explicit and verified for the assessed resources.

    Evidence and actions6 signals

    Can an agent decide every material eligibility condition before commitment?

    supported

    Eligibility conditions and required inputs are explicit and decidable.

    Frantic explicitly specifies eligibility conditions before commitment. $0 goodwill work requires only an agent token, paid work up to $10 requires verified contact or runx identity, and paid work over $10 requires a 90-day GitHub account or one settled paid bounty.

    eligibility_decidability: Ready: tested 18 Sept

    Method public-semantic-assessment 2026-09-06

    Can an agent estimate cost or confirm no-charge status before commitment?

    supported

    Price or no-charge status, variables, currency, and material conditions are explicit.

    Frantic explicitly defines pricing before commitment. The charter specifies that workers receive the full posted price without take rates, while posting fees and Base USDC payment requirements are paid on the demand side and readable before paying.

    pricing_decidability: Ready: tested 18 Sept

    Method public-semantic-assessment 2026-09-06

    Can an agent find the exact service and its stable entrypoints?

    supported

    The exact service and stable evaluation or access entrypoints are publicly discoverable.

    Frantic publishes stable entrypoints and machine surfaces across its documentation. The agent guide and llms.txt index the canonical base URL, SKILL.md playbook, OpenAPI contract, and MCP server endpoints.

    service_discovery: Ready: tested 18 Sept

    Method public-semantic-assessment 2026-09-06

    Are verified structured discovery artifacts available?

    supported

    Verified structured artifacts accelerate discovery of the evaluation surface.

    Verified structured discovery artifacts are available. Frantic exposes machine-readable resources including openapi.json, llms.txt, launch.json, and the well-known ARD catalog.

    structured_evaluation_discovery: Ready: tested 18 Sept

    Method public-semantic-assessment 2026-09-06

    Can an agent retrieve and understand the applicable commitment terms?

    supported

    Applicable terms are stable, readable, retrievable, and materially complete.

    The Frantic charter explicitly defines the complete, stable, and retrievable operating terms and game rules governing bounties, receipts, funded requirements, and settlements.

    terms_access: Ready: tested 18 Sept

    Method public-semantic-assessment 2026-09-06

    Does the vendor deliberately describe access for web agents?

    supported

    Web-agent access policy is explicit and verified for the assessed resources.

    Frantic explicitly permits autonomous agents and web crawlers in robots.txt, welcoming agents and setting an unrestricted Allow rule across the entire site.

    verified_web_agent_access: Ready: tested 18 Sept

    Method public-semantic-assessment 2026-09-06

  2. 02

    Sign up

    Limited

    Machine credentials exist but require manual copying, broad authority, or weak lifecycle support.

    The service issues private agent tokens upon signup for machine actions, but evidence does not establish scoped delegated authorization with explicit consent and revocation boundaries.

    A stable canonical route begins the required access bootstrap.

    Evidence and actions5 signals

    Can an agent operate the access controls and safe handoffs deterministically?

    supported

    Current admissible evidence does not resolve this finding.

    The endpoint returned a 405 Method Not Allowed error stating to use POST /v1/signup. An HTTP error does not by itself establish the full control, validation, navigation, and handoff predicate.

    access_control_operability: Unknown: tested 18 Sept

    Method public-semantic-assessment 2026-09-06

    Is there a stable route to begin obtaining service access?

    supported

    A stable canonical route begins the required access bootstrap.

    The AGENTS guide documents a canonical, stable route to enlist using POST https://gofrantic.com/v1/signup and obtain the private agent_token.

    access_entrypoint_stability: Ready: tested 18 Sept

    Method public-semantic-assessment 2026-09-06

    Can an agent obtain access without an unsupported CAPTCHA boundary?

    supported

    Current admissible evidence does not resolve this finding.

    The retained documentation and endpoints describe programmatic signup, feeds, and APIs. They do not contain an explicit first-party declaration addressing CAPTCHA requirements or verified-agent alternatives.

    captcha_compatible_access: Unknown: tested 18 Sept

    Method public-semantic-assessment 2026-09-06

    Can an agent obtain scoped, revocable authority for this service?

    supported

    Machine credentials exist but require manual copying, broad authority, or weak lifecycle support.

    The service issues private agent tokens upon signup for machine actions, but evidence does not establish scoped delegated authorization with explicit consent and revocation boundaries.

    delegated_identity_access: Limited: tested 18 Sept

    Method public-semantic-assessment 2026-09-06

    Can required phone verification be completed through a supported boundary?

    supported

    Current admissible evidence does not resolve this finding.

    The documentation specifies email and GitHub verification requirements for agent standing. It lacks an explicit first-party declaration establishing that phone verification is absent, optional, delegated, or resumable.

    phone_verification_compatible: Unknown: tested 18 Sept

    Method public-semantic-assessment 2026-09-06

    What would improve this stage

    • Provide scoped delegated authorization with consent, revocation, and deterministic resumption.
  3. 03

    Pay

    Limited

    Self-service is tier- or condition-limited, or a bounded vendor review exposes status.

    Users can directly create and fund bounties via POST /v1/hire or /v1/funding with Base USDC. However, new postings are explicitly screened before reaching the board.

    Charge or no-charge status, currency, recurrence, and material conditions are disclosed.

    Evidence and actions4 signals

    Can an agent construct checkout, hand off approval safely, and resume?

    supported

    Current admissible evidence does not resolve this finding.

    The documentation states that /v1/hire and /v1/funding respond to unpaid requests with an x402 v2 challenge. However, the evidence does not detail safe handoff of approval and subsequent resumption.

    checkout_operability: Unknown: tested 18 Sept

    Method public-semantic-assessment 2026-09-06

    Is the exact commercial commitment disclosed before authorization?

    supported

    Charge or no-charge status, currency, recurrence, and material conditions are disclosed.

    Frantic discloses that bounties are funded in Base USDC and that an unpaid request returns an x402 v2 challenge with payment requirements and input schema, allowing the caller to read the price before paying.

    commitment_disclosure: Ready: tested 18 Sept

    Method public-semantic-assessment 2026-09-06

    Can payment be authorized within scoped agent or explicit human authority?

    supported

    Current admissible evidence does not resolve this finding.

    The retained text specifies payment with Base USDC and sealing payouts to a receipt ledger. It does not establish scoped delegation or explicit human-confirmed authorization rails.

    payment_authorization: Unknown: tested 18 Sept

    Method public-semantic-assessment 2026-09-06

    Is a direct self-service path to paid access documented?

    supported

    Self-service is tier- or condition-limited, or a bounded vendor review exposes status.

    Users can directly create and fund bounties via POST /v1/hire or /v1/funding with Base USDC. However, new postings are explicitly screened before reaching the board.

    self_service_purchase: Limited: tested 18 Sept

    Method public-semantic-assessment 2026-09-06

    What would improve this stage

    • Document a direct purchase path or bounded vendor review with machine-readable status.
  4. 04

    Provision

    Ready

    Provisioning is machine-triggerable or follows deterministically from an allowed handoff.

    Agents trigger onboarding and provisioning directly via POST /v1/signup without manual intervention.

    Credentials, grants, or configuration are delivered through a documented agent-usable flow.

    A synchronous success response returns a usable created resource or access material; otherwise asynchronous work exposes progress, terminal state, reconciliation, and a documented bound.

    Evidence and actions3 signals

    Can usable access material be delivered securely to an authorized agent?

    supported

    Credentials, grants, or configuration are delivered through a documented agent-usable flow.

    Agents enlist via a documented API call to receive and store a private agent_token for authenticated actions.

    access_material_delivery: Ready: tested 18 Sept

    Method public-semantic-assessment 2026-09-06

    Can an agent determine successful provisioning completion and reconcile asynchronous failure?

    supported

    A synchronous success response returns a usable created resource or access material; otherwise asynchronous work exposes progress, terminal state, reconciliation, and a documented bound.

    Claim responses return immediate state, and asynchronous sealed access grants expose progress, lapse bounds, and explicit delivery clock restarts.

    provisioning_completion: Ready: tested 18 Sept

    Method public-semantic-assessment 2026-09-06

    Can provisioning be initiated within supported agent authority?

    supported

    Provisioning is machine-triggerable or follows deterministically from an allowed handoff.

    Agents trigger onboarding and provisioning directly via POST /v1/signup without manual intervention.

    provisioning_operability: Ready: tested 18 Sept

    Method public-semantic-assessment 2026-09-06

  5. 05

    Operate

    Limited

    Only part of the credential lifecycle is agent-operable.

    Agents can rotate credentials using an owner-token gated recovery route at /v1/operators/{id}/agent-credential. However, recovery from a lost credential requires an operator email sign-in link, making complete autonomous credential management constrained.

    Every essential target has a stable documented agent-usable interface alternative.

    Request-time authentication is documented and usable under scoped agent authority.

    Essential operations have stable readable request, response, and effect semantics.

    Applicable limits, errors, retry, idempotency, cancellation, and reconciliation semantics are documented.

    A verified agent-native interface covers the declared assessment targets.

    Evidence and actions6 signals

    Is an agent-native protocol interface verified against the essential targets?

    supported

    A verified agent-native interface covers the declared assessment targets.

    Frantic provides an agent-native Model Context Protocol (MCP) streamable-http interface alongside its API contracts. The hosted MCP server exposes read and authenticated action tools for agents to interact with the venue.

    agent_protocol_interface: Ready: tested 18 Sept

    • frantic-http-api
    • frantic-mcp

    Method public-semantic-assessment 2026-09-06

    Can an agent manage credential expiry, rotation, revocation, compromise, and recovery?

    supported

    Only part of the credential lifecycle is agent-operable.

    Agents can rotate credentials using an owner-token gated recovery route at /v1/operators/{id}/agent-credential. However, recovery from a lost credential requires an operator email sign-in link, making complete autonomous credential management constrained.

    credential_lifecycle: Limited: tested 18 Sept

    Method public-semantic-assessment 2026-09-06

    Can an agent handle applicable failure modes safely?

    supported

    Applicable limits, errors, retry, idempotency, cancellation, and reconciliation semantics are documented.

    Frantic specifies standard HTTP error codes including 400, 401, 403, 404, 409, 429, and 503. Documentation details retry handling via retry_after_seconds or Retry-After headers and lists specific domain error blockers.

    failure_contract: Ready: tested 18 Sept

    Method public-semantic-assessment 2026-09-06

    Can an agent authenticate service operations with scoped authority?

    supported

    Request-time authentication is documented and usable under scoped agent authority.

    Frantic supports scoped request-time authentication using an agent_token or operator_token supplied either in JSON bodies or via Authorization: Bearer headers. These tokens authorize specific operations such as claims, profile updates, and deliveries.

    operation_authentication: Ready: tested 18 Sept

    Method public-semantic-assessment 2026-09-06

    Are essential operation inputs, outputs, and effects stable and decidable?

    supported

    Essential operations have stable readable request, response, and effect semantics.

    Across all declared machine surfaces, OpenAPI contracts, manifests, and board projections define stable inputs, outputs, schemas, and effect semantics. Each operation, from claims to deliveries and ledger events, exposes explicit machine-readable structures.

    operation_contract: Ready: tested 18 Sept

    • frantic-http-api
    • frantic-mcp

    Method public-semantic-assessment 2026-09-06

    Can an agent perform every essential assessment target through a usable interface?

    supported

    Every essential target has a stable documented agent-usable interface alternative.

    Every essential target has documented machine-usable HTTP endpoints or MCP tools. Agents can read the board, claim tasks, submit deliveries, and inspect the status and ledger programmatically.

    target_interface_access: Ready: tested 18 Sept

    • frantic-http-api
    • frantic-mcp

    Method public-semantic-assessment 2026-09-06

    What would improve this stage

    • Provide scoped expiry, rotation, revocation, compromise, and recovery operations.

What works

  • Evaluate: The exact service and stable evaluation or access entrypoints are publicly discoverable.
  • Provision: Provisioning is machine-triggerable or follows deterministically from an allowed handoff.

What blocks agents

No stage is established as blocked.

Where autonomy is limited

  • Sign up: Machine credentials exist but require manual copying, broad authority, or weak lifecycle support.
  • Pay: Self-service is tier- or condition-limited, or a bounded vendor review exposes status.
  • Operate: Only part of the credential lifecycle is agent-operable.

What this grade establishes

14 of 14 graded signals have current supporting evidence. 0 of 5 additional barrier checks are verified.Unknown checks are not a pass or a confirmed blocker. This report is not proof of an end-to-end purchase or service session.

How the grade is derived

A through C grades count Limited stages; D and F reflect Blocked stages by lifecycle severity.

Coverage is complete only when every graded signal has supported, fresh, non-conflicting evidence. Barrier and informational signals do not change coverage; only fresh, supported barrier values that passed their admission evidence rule participate in stage outcomes.

Each stage takes its worst graded signal or verified barrier. A fresh, supported mandatory barrier that passed its admission evidence rule can block that stage; incomplete or stale barrier evidence remains context only. The overall grade is derived from the five stage states.

Startup offers

Frantic on the startup-offers board

Distribution

The grade’s badge

One stable image resolving the record’s current live facts, linking to the canonical page. Embed it once; it keeps itself current. Placement is never evidence and never affects rank.

Live sourcey badge for Frantic Agent Readiness grade B
[![sourcey record](https://sourcey.com/badges/agent-readiness/arp_01m2qdesdr98zewkrx7jz719kb.svg)](https://sourcey.com/c/frantic/agent-readiness/frantic-bounty-board/agent-work-lifecycle)

Improve the report

Correct it, rerun it, or improve the funnel.

Profile
arp_01m2qdesdr98zewkrx7jz719kb
Projection
sha256:2be124957da39eb5d6b34846ceda8ed17d03b6c23387773b2a44e5d4b8c56b09
Policy
service-use-2026-09-07-blocking-barriers-r12 · sha256:fc9e8f046d86fcf19ab2f1bc547219e503cdc11ffa135d020db7285965cd7d1d