← Leaderboard
7.8 L3

Github

Native Assessed · Docs reviewed · Mar 11, 2026 Confidence 0.85 Last evaluated Mar 11, 2026

Score breakdown

Dimension Score Bar
Execution Score

Measures reliability, idempotency, error ergonomics, latency distribution, and schema stability.

8.5
Access Readiness Score

Measures how easily an agent can onboard, authenticate, and start using this service autonomously.

6.8
Aggregate AN Score

Composite score: 70% execution + 30% access readiness.

7.8

Autonomy breakdown

P1 Payment Autonomy
8.0

GitHub Actions billing is API-accessible; Marketplace subscriptions possible

G1 Governance Readiness
9.0

Excellent RBAC via teams/orgs, comprehensive audit logs, SOC2 certified

W1 Web Agent Accessibility
7.0

Good dashboard but complex navigation; API is excellent

Overall Autonomy 8.0/10
Ready for agent use

Active failure modes

  • HIGH

    Secondary rate limits on content creation

    Beyond the primary 5000 req/hour limit, GitHub enforces undocumented secondary rate limits on write operations (issues, comments, PRs). Agents creating multiple items in quick succession get 403s.

    Agent impact: Agent workflows that create multiple issues or PR comments in sequence fail unpredictably. The 403 looks different from a permissions error.

    Workaround: Add 1-second delays between write operations. Check for "secondary rate limit" in error message body. Implement progressive backoff.

    common rate-limiting
  • MEDIUM

    Fine-grained PAT scope inheritance confusion

    Fine-grained personal access tokens have complex permission inheritance across org/repo/endpoint. Agents may have partial access that produces confusing 404s (not 403s) on resources they cannot see.

    Agent impact: Agent receives 404 for repos that exist but are invisible to its token scope. May incorrectly conclude the resource does not exist.

    Workaround: Use classic PATs for broad access. For fine-grained tokens, explicitly test each required endpoint at startup and fail fast.

    occasional auth
  • MEDIUM

    GraphQL schema deprecation without warning

    GitHub's GraphQL API deprecates fields with minimal notice. Agents relying on deprecated fields get null values instead of errors.

    Agent impact: Agent data pipeline silently receives null for previously-populated fields. Score calculations or reports become inaccurate without obvious errors.

    Workaround: Pin to REST API for critical data paths. Monitor GitHub changelog for GraphQL deprecations. Add null-checks with alerting on critical fields.

    occasional schema

Use in your agent

mcp
get_score ("github")
● Github 7.8 L4 Native
exec: 8.5 · access: 6.8

Trust & provenance

This score is documentation-derived. Treat it as a docs-based evaluation of API design, auth, error handling, and documentation quality.

Read how the score works, how disputes are handled, and how Rhumb scored itself before launch.

Overall tier

L4 Native

7.8 / 10.0

Alternatives

No alternatives captured yet.