nonlooped/ContextLevy

Estimate AI agent context overhead introduced by a pull request diff.

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
github-tokenFallback token with pull-requests: write when GitHub App auth is not configuredno
create-checkPublish a GitHub Check Run named ContextLevy (requires checks: write)notrue
upload-sarifUpload SARIF for Code Scanning annotations (requires security-events: write)notrue
app-client-idContextLevy GitHub App ID. Falls back to CONTEXTLEVY_APP_ID or CONTEXTLEVY_APP_CLIENT_ID env var.no
app-private-keyContextLevy GitHub App private key PEM. Falls back to CONTEXTLEVY_APP_PRIVATE_KEY env var.no
app-installation-idOptional installation ID override. Falls back to CONTEXTLEVY_APP_INSTALLATION_ID env var.no
namedescription
total-estimated-tokensTotal estimated AI-context tokens added by this PR (integer as string)
analyzed-file-countNumber of changed files included in the estimate (integer as string)
token-sourceAuth source used for the run: app, github-token, or GITHUB_TOKEN
estimation-modeToken estimation mode used for this run: simple or tokenizer
risk-levelAggregated PR context risk level: Low, Medium, High, or Critical
check-conclusionGitHub Check Run conclusion when create-check is enabled
badge-urlshields.io badge URL for PR context risk
badge-markdownMarkdown image tag for PR/README badges
sarif-pathPath to the generated SARIF file in the workspace
sarif-uploadedWhether SARIF was uploaded to GitHub Code Scanning (true/false)