evaluate-pattern-adoption

Evaluate Pattern Adoption

Run model-backed research only in the user's interactive local Codex client. Keep GitHub Actions deterministic and credentialless for this capability.

Establish the execution boundary

1. Work from the repository root in a local Codex app, CLI, or IDE session signed in with the user's ChatGPT account. Prefer the Codex app.
2. Confirm that evaluation will use the active Codex authentication. Local execution alone does not determine billing: a signed-in ChatGPT-plan client uses that plan's Codex allowance or credits, while API-key authentication is billed as OpenAI Platform API usage.
3. Do not continue when GITHUB_ACTIONS=true, when an evaluator API-key environment variable is present, or when the active client is authenticated with an API key. Never request, read, copy, print, or store a provider key.
4. Do not treat the user's initial request as approval to spend agent credits or publish results. Both gates below occur after the relevant plan or diff exists.
5. Fetch origin, then start from a dedicated branch or worktree whose HEAD is the current origin/main. Require git status --short to be empty before planning. Do not stash, discard, absorb, or work around unrelated changes; stop and move to a clean worktree instead.
6. Confirm there are no unrelated tracked or untracked changes under verification/ or in experiments/NOTES.md. The final scope validator intentionally examines the whole worktree and fails on every changed path outside the approved run.

Read references/evidence-methodology.md completely before starting research.

Build the deterministic plan

Choose one explicit scope:

• stale — up to 10 missing, legacy, or stale patterns by default;
• stable — every stable pattern in patterns.yaml;
• exploratory — every pattern in experiments/README.md;
• all — stable plus exploratory patterns and one discovery unit;
• single — one exact catalog name; or
• discovery — discovery only, with no evidence pattern.