{"id":"email-agent-readiness-v1","version":"1.0.0","publishedAt":"2026-08-17","status":"Protocol published; All Them APIs credentialed reruns pending","agent":"Claude Code","modelPolicy":"Record the immutable model ID returned by every run; never use an unversioned alias in published results.","taskPrompt":"You are working in a new Node.js repository. Integrate the {{PROVIDER}} email API and complete this task:\n\n1. Install the provider's official server-side SDK when one exists; otherwise use its documented REST API.\n2. Read credentials only from {{CREDENTIAL_ENV}}. Never print, copy, or commit the credential.\n3. Implement a script that sends one transactional verification email to {{TEST_RECIPIENT}} with the subject \"All Them APIs verification\" and a unique run ID in the body.\n4. Use the provider's documented sandbox, test mode, or non-delivery recipient when available. Do not silently replace the requested recipient or return demo data.\n5. Add an automated test for request construction and a README containing install, run, and cleanup commands.\n6. Run the test and the script. Record the provider message ID or the exact blocking error.\n\nSuccess requires a provider-confirmed message ID or a documented non-delivery test response, passing local tests, no secret in the repository, and no change to the requested behavior. If authorization or account state blocks the task, stop and report the exact step.","command":"mkdir -p artifacts workspace\ncd workspace\ngit init --quiet\nnpm init -y >/dev/null\n\nclaude -p \"$(cat ../prompt.md)\" \\\n  --model \"$CLAUDE_MODEL_ID\" \\\n  --max-turns 40 \\\n  --output-format stream-json \\\n  --verbose \\\n  --dangerously-skip-permissions \\\n  | tee ../artifacts/trace.jsonl\n\nnpm test 2>&1 | tee ../artifacts/test.log\ngit diff --no-index /dev/null . > ../artifacts/workspace.diff || true","sandbox":[{"label":"Base image","value":"node:22-bookworm-slim, pinned by digest for a published run"},{"label":"Resources","value":"2 vCPU, 4 GB RAM, 10-minute wall-clock limit"},{"label":"Filesystem","value":"Fresh writable repository; destroyed after artifact export"},{"label":"Network","value":"Public web and provider API allowed; private network ranges blocked"},{"label":"Credentials","value":"One pre-provisioned least-privilege key or grant, injected as an environment variable"},{"label":"Packages","value":"No provider SDK preinstalled; package and lock files preserved"},{"label":"Human help","value":"Only account authorization or CAPTCHA; every intervention is timestamped and counted"},{"label":"Runs","value":"Three fresh runs per provider; median reported, all failures retained"}],"successCriteria":["Provider-confirmed message ID or documented non-delivery test response","Requested recipient behavior is preserved","Local request-construction test passes","Credential remains outside source, logs, and generated artifacts","Install, execution, and cleanup instructions are present"],"requiredArtifacts":["Prompt and immutable model ID","Container image digest and resource limits","Stream JSON agent trace","Final workspace diff and lockfile","Test output and provider response with secrets removed","Timing, token, cost, tool-call, error, and intervention counts","Evaluator decision with a written failure reason"],"currentRuns":[{"rank":1,"provider":"Resend","publicEvidence":"Public task + setup runs","reproduction":"Recorded values checked; credentialed rerun pending"},{"rank":2,"provider":"AgentMail","publicEvidence":"Public task + setup runs","reproduction":"Recorded values checked; credentialed rerun pending"},{"rank":3,"provider":"Postmark","publicEvidence":"Public setup run","reproduction":"Recorded values checked; credentialed rerun pending"},{"rank":4,"provider":"Mailgun","publicEvidence":"Public setup run","reproduction":"Recorded values checked; credentialed rerun pending"},{"rank":5,"provider":"Loops","publicEvidence":"First-party integration sources","reproduction":"Documentation checked; first independent run pending"},{"rank":6,"provider":"Nylas","publicEvidence":"Public task run","reproduction":"Recorded values checked; credentialed rerun pending"},{"rank":7,"provider":"SendGrid","publicEvidence":"Blocked public setup run","reproduction":"Blocked result checked; credentialed rerun pending"}]}