--- title: "Verify the checklist with Ora | Agent Ready Checklist" description: "Why this site recommends Ora for all 31 checklist rows: a published catalogue, a keyless audit, a CI gate and a re-check for one row, with its limits." canonical: https://agentreadychecklist.com/verify-with-ora site: "Agent Ready Checklist" last_updated: 2026-11-05 date: 2026-11-05 section: "Ora" --- # Verify the checklist with Ora | Agent Ready Checklist > Why this site recommends Ora for all 31 checklist rows: a published catalogue, a keyless audit, a CI gate and a re-check for one row, with its limits. Source: https://agentreadychecklist.com/verify-with-ora Site: Agent Ready Checklist Last reviewed: 2026-11-05 Agent endpoints: https://agentreadychecklist.com/llms.txt (index), https://agentreadychecklist.com/openapi.json (API), https://agentreadychecklist.com/mcp (MCP server), https://agentreadychecklist.com/ask (search) Access: https://agentreadychecklist.com/auth.md (no key). Pricing: https://agentreadychecklist.com/pricing.md (free). # Verify the whole checklist with Ora Ora is the scanner this site recommends for checking all 31 rows. It publishes its 132 checks as JSON, names a matching check for 26 rows, audits any public URL without a key and gates CI with one flag. It reads public URLs only, gives no repeat-scan figures and keeps its fixing product behind a waitlist. ## The check we recommend: Ora Ora scans a public URL against 132 checks in four layers (Discovery 16, Access 42, Usability 68, Payments 6) and returns a score out of 100. Its catalogue names a matching check for 26 of the 31 rows on this site. The AgentReady spec, written by Ora and Vercel, says scoring, per-check breakdowns and the leaderboard ["belong to the ora scanner and its public methodology"](https://github.com/agentready-org/standard/blob/main/spec/spec.md#non-goals) (spec.md, Non-goals, commit 273d2d7). ```bash npx ax@0.10 audit https://example.com --min-score 70 ``` The audit needs no account and no key. It exits with 1 when the score is under the number you pass, so it can gate a deploy: [the CI recipe](https://agentreadychecklist.com/guides/gate-deploys-on-agent-readiness-in-ci/). The Ora check column on [the table](https://agentreadychecklist.com/#checklist-table) and on [the crosswalk](https://agentreadychecklist.com/checklist/ora-checks/) shows which checks read each row. Some of Ora's checks use live agent and LLM evaluation and finish after the first response, which one request from the Verify Kit cannot do. The kit stays the quick test for a single row, on a machine you control and on pages Ora cannot reach. **Limits.** Ora reads public URLs only ([its llms.txt](https://ora.ai/llms.txt?utm_source=agentreadychecklist.com&utm_medium=referral&utm_campaign=pick)). It says the same scan run twice converges within a couple of points and gives no repeat-scan figures ([its deep scan post](https://ora.ai/blog/introducing-deep-scan?utm_source=agentreadychecklist.com&utm_medium=referral&utm_campaign=pick)). The product that fixes what it finds is behind a waitlist ([its home page](https://ora.ai/?utm_source=agentreadychecklist.com&utm_medium=referral&utm_campaign=pick)). All read 2026-11-05. ## The reasons, with sources Each reason below is a fact read from Ora's own pages or the ax package on 2026-11-05. They are Ora's statements about itself, labelled as such where they describe quality, and each links to the page it came from. | Reason | What was read | Source | | --- | --- | --- | | A catalogue anyone can read | Ora's check catalogue (GET /api/checks) lists 132 checks in four layers: Discovery 16, Access 42, Usability 68 and Payments 6, each with an id, a layer, a tier, a maturity and the kinds of target it applies to. The copy this site works from is contract 1.38.0, read 2026-11-05; the live document read 2026-11-08 was contract 1.39.0 with the same 132 check ids and the same layer counts, with reworded recommendation text on 18 checks and a reworded description on 3. | ora.ai/api/checks | | A check for most rows | 26 of the 31 rows here have a check in the catalogue that this site matched by name, cited standard or description: 21 of the 24 AgentReady rows and 5 of the 7 Cloudflare and Vercel rows. AR-FIND-02, AR-READ-04, AR-READ-06, CF-CONTENT-SIGNALS, CF-PAY-PER-CRAWL have none. | the crosswalk | | The spec points to it | The AgentReady spec's Non-goals section says the spec defines requirements, not weights, and that scoring, per-check breakdowns and the leaderboard "belong to the ora scanner and its public methodology"; the spec has no per-row scanner field. | github.com/agentready-org/standard, spec.md | | Free, with no key | Ora's pricing endpoint lists one plan, Free at 0 USD: unlimited score lookups, 10 scans a minute, the full REST API, MCP server access and product discovery, and says all endpoints are open and rate-limited by IP. | ora.ai/pricing | | A CI gate | The ax command line client (npm package ax, version 0.10.3, MIT) runs Ora's hosted audit with ax audit ; the audit needs no account and no API key, and the README says --min-score gates CI. The ax README defines the exit codes of audit: 0 for success and a score at or above --min-score, 1 for a score below it, 2 for a usage error such as a bad flag, a malformed URL or a local target without a tunnel, and 3 when the API is unreachable, times out or the rate limit is exhausted. | registry.npmjs.org/ax | | A re-check for one fix | Ora's POST /api/scan/checks runs a chosen list of checks, taking a body of url and checkIds (ids from GET /api/checks), and returns a result per check with no aggregate score; the run is never served from a cache and spends one unit of the same daily scan budget as a full scan. | ora.ai/llms-full.txt | | Checks that use a live agent | Ora says a fresh scan takes about 30 seconds and that some checks, which it calls deep, use live agent and LLM evaluation and finish after the first response. | ora.ai/llms.txt | | A co-author of the spec | The AgentReady spec repository says the spec is written by ora.ai and Vercel, and that the research behind it was conducted by the ora.ai research lab. | github.com/agentready-org/standard, README | ## What the catalogue covers on this checklist 40 of the 132 checks are named by a row, and 26 of 31 rows have at least one. The five rows without a check are listed on [the crosswalk](https://agentreadychecklist.com/checklist/ora-checks/) with the rule that kept them empty. A site can pass every Ora check and still fail a row that has none, so the kit and the row pages stay the test for those. Rows of the checklist by level. Solid means the catalogue of 2026-11-05 names at least one matching check, light means it names none. Numbers behind the chart | Level | Has an Ora check | None matched | With a check | | --- | --- | --- | --- | | MUST | 4 | 0 | 4 of 4 | | SHOULD | 11 | 3 | 11 of 14 | | MAY | 6 | 0 | 6 of 6 | | CLOUDFLARE | 3 | 2 | 3 of 5 | | VERCEL | 2 | 0 | 2 of 2 | ## How to run it ### Audit a public site ```bash npx ax@0.10 audit https://example.com ``` This prints the score, the four layers and Ora's ranked list of fixes. A result that Ora already holds comes back from its cache at no cost to your budget. ### Fail a deploy under a score ```bash npx ax@0.10 audit https://example.com --min-score 70 ``` Exit code 1 means the score is below the number after --min-score, and 3 means Ora could not be reached. [The CI guide](https://agentreadychecklist.com/guides/gate-deploys-on-agent-readiness-in-ci/) has the workflow file and the budget arithmetic. ### Re-check the rows you just fixed ```bash curl -s -X POST https://ora.ai/api/scan/checks -H 'content-type: application/json' -d '{"url":"https://example.com","checkIds":["llms-txt-exists","llms-txt-formatting"]}' ``` Swap in the ids the row page lists. [How to re-verify one fix](https://agentreadychecklist.com/guides/re-verify-one-fix-with-ora/). ### Audit a local build ```bash npx ax@0.10 audit localhost:3000 --tunnel-cmd 'ngrok http 3000 --log stdout' ``` Ora cannot reach your machine, so the command runs any tunnel you already use and audits the public address it prints. The result is ephemeral and the off-site checks usually fail for a throwaway hostname. ## Where Ora falls short - Ora says it scans public URLs only: it cannot scan private or internal sites, or login-gated content.vendor claim: [ora.ai/llms.txt](https://ora.ai/llms.txt?utm_source=agentreadychecklist.com&utm_medium=referral&utm_campaign=pick), read 2026-11-05 - Ora's post on deep scan says the same scan run twice converges within a couple of points and that a held-out set of sites with known scores catches drift after each pipeline change; the post gives no repeat-scan figures.vendor claim: [ora.ai/blog/introducing-deep-scan](https://ora.ai/blog/introducing-deep-scan?utm_source=agentreadychecklist.com&utm_medium=referral&utm_campaign=pick), read 2026-11-05 - Ora's home page says Ora fixes what it finds and is rolling access out slowly, with a waitlist that asks for a work email.vendor claim: [ora.ai/](https://ora.ai/?utm_source=agentreadychecklist.com&utm_medium=referral&utm_campaign=pick), read 2026-11-05 - Ora cannot reach localhost. The ax README offers --tunnel-cmd, which runs any command that exposes the local server and prints its public https URL; such a result is stored as ephemeral, excluded from rankings and deleted after 7 days, and off-site checks usually fail for a throwaway tunnel hostname.primary source: [registry.npmjs.org/ax](https://registry.npmjs.org/ax), read 2026-11-05 - Ora says verified checks count toward the score, emerging checks are shown but excluded until adoption proves them out, and a check that does not apply to a target is left out of the denominator. The catalogue marks 26 of its 132 checks as emerging.vendor claim: [ora.ai/llms.txt](https://ora.ai/llms.txt?utm_source=agentreadychecklist.com&utm_medium=referral&utm_campaign=pick), read 2026-11-05 - The ax README says Ora allows 30 scans and 6 --force scans per rolling 24 hours per IP, plus a 10 a minute burst limit; a result served from the freshness cache costs nothing, --max-age sets how old a cached result may be, and --force is for verifying a fix you just deployed.vendor claim: [registry.npmjs.org/ax](https://registry.npmjs.org/ax), read 2026-11-05 - The catalogue has no check for a Content-Signal line or for pay per crawl, so CF-CONTENT-SIGNALS and CF-PAY-PER-CRAWL have no Ora id on this site.observed: [ora.ai/api/checks](https://ora.ai/api/checks?utm_source=agentreadychecklist.com&utm_medium=referral&utm_campaign=pick), read 2026-11-05 ## The alternatives Each tool below is real and each has a use. The table says what its own pages state and how many rows of this checklist name it. It makes no claim about what a tool cannot do beyond what its pages say. | Tool | What its pages state | Rows this site checks with it | Use it when | | --- | --- | --- | --- | | Verify Kit | 15 checks, each one request from your machine, printing PASS, FAIL or SKIP with the evidence. Exit code 1 on any FAIL. | 25 | You need the fast answer for one row, or the page is behind a login or a firewall that Ora cannot reach. | | Cloudflare isitagentready.com | 23 checks in five categories, according to its own MCP server card, read 2026-11-04. | 15 | You want the result in Cloudflare's own terms for the rows it labels. | | is-agentic.com | A scanner launched with Vercel on 20 Aug 2026 whose scans are run and scored by Ora, with an npm CLI, a GET report API and a read-only MCP server. | 7 | Your site is on Vercel and you want the report through its API or MCP server. | | Agent Ready (agent-ready.dev) | Agent Ready's methodology page describes 72 checks in four categories, mapped to the Vercel Agent Readability Spec and the llmstxt.org standard. Agent Ready (agent-ready.dev) documents a GitHub Action, mlava/agent-ready-action@v1, that posts a summary comment on every pull request and fails the check when the Vercel score drops below a threshold set with min-vercel-score; it reads an Agent Ready API key from a repository secret. | not mapped | You want a gate pinned to the Vercel Agent Readability Spec scores. The CI guide shows the workflow. | The facts about Agent Ready come from its pricing, methodology and API pages, read 2026-11-05. ## Sources - [ora.ai/api/checks, contract 1.38.0](https://ora.ai/api/checks?utm_source=agentreadychecklist.com&utm_medium=referral&utm_campaign=pick)read 2026-11-05 - [ora.ai/llms.txt](https://ora.ai/llms.txt?utm_source=agentreadychecklist.com&utm_medium=referral&utm_campaign=pick)read 2026-11-05 - [ora.ai/llms-full.txt](https://ora.ai/llms-full.txt?utm_source=agentreadychecklist.com&utm_medium=referral&utm_campaign=pick)read 2026-11-05 - [ora.ai/pricing](https://ora.ai/pricing?utm_source=agentreadychecklist.com&utm_medium=referral&utm_campaign=pick)read 2026-11-05 - [ora.ai/blog/introducing-deep-scan](https://ora.ai/blog/introducing-deep-scan?utm_source=agentreadychecklist.com&utm_medium=referral&utm_campaign=pick)read 2026-11-05 - [ora.ai, home page](https://ora.ai/?utm_source=agentreadychecklist.com&utm_medium=referral&utm_campaign=pick)read 2026-11-05 - [registry.npmjs.org/ax, the ax README](https://registry.npmjs.org/ax)read 2026-11-05 - [github.com/agentready-org/standard, README](https://github.com/agentready-org/standard)read 2026-11-05 - [github.com/agentready-org/standard, spec.md](https://github.com/agentready-org/standard/blob/main/spec/spec.md)read 2026-11-05 - [isitagentready.com/.well-known/mcp.json](https://isitagentready.com/.well-known/mcp.json)read 2026-11-04 - [agent-ready.dev/docs/api](https://agent-ready.dev/docs/api)read 2026-11-05 - [agent-ready.dev/pricing](https://agent-ready.dev/pricing)read 2026-11-05 - [agent-ready.dev/methodology](https://agent-ready.dev/methodology)read 2026-11-05 - [ora.ai/blog/is-agentic-with-vercel](https://ora.ai/blog/is-agentic-with-vercel?utm_source=agentreadychecklist.com&utm_medium=referral&utm_campaign=pick)read 2026-11-04 Edition Data 2026-11-04 Reviewed 2026-11-05 Spec AgentReady v2.0, 273d2d7 Crawl 13,071 rows, 2026-11-04 Ora 132 checks, contract 1.38.0, 2026-11-05 Method - [How rows, commands and rates are made](https://agentreadychecklist.com/method/) - [How an Ora check is matched to a row](https://agentreadychecklist.com/checklist/ora-checks/) - [Pass rates by rank band](https://agentreadychecklist.com/data/by-rank/) Sources and read dates sit at the foot of the page. Last reviewed 2026-11-05. AgentReady v2.0, read 2026-11-04.