GitHubgithub.com

ScoredJul 23, 2026, 06:59 PM

GitHub's API program performs well on discoverability and doc parseability, but has two critical gaps that directly limit partner and agent success: agents lack structured instructions to understand how to navigate and use the API surface, and there is no runnable, test-backed collection giving partners and their coding agents a verified, executable starting point. Prioritizing an agent instructions file and a runnable collection with test scripts will unblock both human partners and AI-driven integrations from day one — followed by closing the auth declaration and quickstart gaps to compress the time to a partner's first production call.

API DesignA clean, typed, well-governed API contract agents can reason about4 pass0 warn1 fail79B
SignalPointsFindingsRationale
passMachine-readable, versioned contractvia spec25/25Versioning declared (info.version="1.1.4") and media-type-versioning detected. Investigated: spec 100%, docs 100%.A current OpenAPI version with a declared versioning scheme lets agents reason about the contract.
passSchema coverage & depthvia sdk25/255/5 (100%) public params are fully typed (no any/**kwargs). Analyzer confirms all methods have a derivable input schema. Investigated: sdk 100%, spec 67%.Typed, complete request/response schemas are what make agent function-calling possible.
passSecurity & governance hygienevia wellknown15/15security.txt valid at https://github.com/.well-known/security.txt (Contact + unexpired Expires). Investigated: wellknown 100%, spec 0%.No leaked secrets, no critical lint violations, no OWASP API Top-10 spec smells, and a published vulnerability-disclosure channel.
passExample coveragevia sdk10/10README is present and includes a runnable quickstart. Investigated: sdk 100%, spec 0%.Examples carry shape semantics schemas under-specify — for humans and agents alike.
failAuth declared & discoverablevia spec0/25No securitySchemes declared. Investigated: spec 0%, docs 0%.Agents can only authenticate when auth is declared, scoped, and discoverable.
Developer ExperienceThe context both developers and agents need to integrate fast — onboarding, code samples, complete descriptions and worked examples3 pass0 warn1 fail75B
SignalPointsFindingsRationale
passSelf-service developer portalvia docs29/29Signup page at https://github.com/sign-up; no free-tier language detected in docs/pricing. Investigated: docs 100%.Self-serve key/account creation is the fast first call for partners, with no sales gate.
passDescription completenessvia spec15/1598% of operations + parameters have substantive descriptions. Investigated: spec 100%, sdk 74%.Complete descriptions are the context humans and agents need to use endpoints.
passChangelog publishedvia sdk13/13Newest official SDK activity 1 day(s) ago. Investigated: sdk 100%, spec 0%, docs 0%.A published changelog lets partners track changes without surprise.
failQuickstart presentvia docs0/25No quickstart/getting-started page found at the conventional paths. Investigated: docs 0%.A quickstart is the fastest path from landing page to first successful call.
naCode samples in docs—/18No surface produced evidence for this capability in this run.Multi-language samples shorten time-to-first-call.
Agent DiscoveryPartners and their agents can find your APIs — llms.txt, registries, crawlable and reachable docs1 pass3 warn0 fail81A
SignalPointsFindingsRationale
passRegistry & SDK presencevia docs28/28Indexed on Context7 (websites/github_en, 43828 snippets). Investigated: docs 100%, sdk 100%, cli 0%.Listing in MCP registries and publishing SDKs puts the API where agents and their tooling look.
warnDocs reachable, not hard auth-gatedvia docs22.5/30Server ignores Accept: text/markdown header (0/50 sampled pages return markdown); 50 rate-limited (HTTP 429). Investigated: docs 75%.Agents can only index and fetch docs they can reach — past auth gates and over correct HTTP semantics.
warnllms.txt present, valid & comprehensivevia docs21.4/30No llms.txt directive found in HTML of any of 50 sampled pages. Investigated: docs 71%, sdk 0%.A valid, comprehensive llms.txt is the machine-readable entry point for agents.
warnCrawlable / AEOvia wellknown6/12No sitemap discoverable via robots.txt or /sitemap.xml on the docs host. Investigated: wellknown 50%.Bots allowed plus a fresh sitemap make docs findable by agent crawlers.
Agent UnderstandingAgents can correctly interpret your APIs — machine-readable errors, consistent descriptions, structured data, parseable docs2 pass1 warn1 fail82A
SignalPointsFindingsRationale
passMachine-readable errors (RFC 9457)via docs28/2815 distinct 4xx/5xx response codes documented. Investigated: docs 100%, spec 50%, sdk 0%.RFC 9457 problem details and a documented error-code inventory let agents parse failures without burning tokens.
passOperation purpose clarityvia spec25/25100% of operations have a clear summary + operationId an agent can select on. Investigated: spec 100%.Agents select the right endpoint from its summary + operationId; clear, named operations make tool-selection reliable — the strongest driver of correct tool choice.
warnAgent-navigable, token-efficient docsvia docs13.8/22No sampled pages support .md URLs (0/50 tested). Investigated: docs 63%.Server-rendered, clean, small-footprint docs are what an agent can cheaply fetch and parse correctly.
failAgent instructions file (AGENTS.md)via wellknown0/10No AGENTS.md at the site root or /.well-known/. Investigated: wellknown 0%.An AGENTS.md gives coding agents explicit setup, auth, and usage instructions to interpret and operate the API — beyond llms.txt's link index.
naDocs structured data—/8No surface produced evidence for this capability in this run.Structured data (JSON-LD/schema.org) on docs pages gives agents an unambiguous parse target and is what answer engines cite. Detected on the JS-rendered head (Firecrawl) for a bounded page budget, so JS-injected JSON-LD is now caught; pages we can't render are excluded rather than failed.
naDescription consistency across surfaces—/7Only 0 surface description(s) with ≥6 tokens available; need at least 2 to compare.Every surface tells the same story about what the product is.
Agent UsabilityAgents have the context to use your APIs reliably, not just find them3 pass0 warn2 fail71B
SignalPointsFindingsRationale
passRate-limit signalingvia spec22/223 distinct rate-limit response headers documented. Investigated: spec 100%, docs 100%.Machine-readable rate-limit headers let agents throttle adaptively.
passPagination documented & consistentvia spec22/22Pagination params detected on 241 list endpoint(s). Investigated: spec 100%, docs 100%, sdk 100%.Consistent, documented pagination lets agents traverse collections.
passSandbox separationvia sdk20/20Sandbox environments are exposed (sandbox). Investigated: sdk 100%, spec 0%, docs 0%.An isolated environment lets agents exercise destructive operations safely.
failIdempotency documentedvia spec0/270% of mutating operations document idempotency. Investigated: spec 0%, docs 0%, sdk 0%.Documented idempotency lets agents retry safely.
failRunnable collection with test scriptsvia platform0/9No test scripts found in the workspace's collections. Investigated: platform 0%.A public, maintained collection with assertions is runnable truth agents validate against.
Resources Discovered

The public resources we found for GitHub — the evidence behind the score. All discovered from public sources; nothing here requires access to your systems.

Agent hintsContext7 (43,828)
APIs analyzed1GitHub v3 REST API
Want to improve your results?