Skip to content
Agents tracked: 501 Releases (7d): 777 Agent status: no reported issuesSince last limit reset: Claude 10d · Codex 8d For AI agents: Markdown Updated Nov 21, 2026
Case study GitHubResults as reported by GitHub

How GitHub expanded secret validity checks with Copilot coding agent

GitHub's Secret Protection team had engineers do the research, then gave Copilot coding agent the repetitive work of adding validators for more leaked-token types. Coverage grew quickly.

The problem

Secret Protection checks whether a leaked credential is still valid by testing it against a harmless API endpoint. Only 32 token types were covered, and adding less common types through the existing framework was slow.

How they did it

  1. Engineers researched which API endpoints could validate each new token type.
  2. A GitHub workflow turned that research into detailed issues that served as prompts for the agent.
  3. Copilot coding agent opened pull requests, and engineers reviewed, tested and asked for changes through PR comments.
  4. New validators first ran in 'darkship' mode to observe results safely.
  5. Copilot then made the configuration changes to fully release them.

Results as reported by GitHub

  • As reported by GitHub: the team went from validating '32 partner token types' to onboarding 'almost 90 new types in just a few weeks'.

These figures are as reported by GitHub in GitHub blog (engineering) ↗ (Aug 28, 2025). GitHub sells the product used here. AgentGid did not measure or independently verify them.

Takeaway. Keep the research and judgment with engineers, then give the agent many similar, well-specified issues to implement.
AgentGid's take

This suits a team with engineers who can research each item and write detailed issues, plus the review capacity to test every PR. The "almost 90 types in a few weeks" figure is GitHub's own report, and the cloud agent draws on monthly AI Credits (Pro includes 1,500 at $10/mo), so heavy batches of issues may use them up. Zed (Free + $10/mo) is an open-source option if you want to try a similar workflow with your own API keys.

The agent used here

Similar use cases

Guides