{"slug":"asymptote-labs-self-verify-beacon-in-sandbox","source_name":"asymptote-labs/self-verify-beacon-in-sandbox","name":"Asymptote Labs/Self Verify Beacon In Sandbox","description":"Verify a Beacon change end to end by running a real Claude Code session inside a disposable Linux cloud sandbox and checking that Beacon captured what the agent actually did. Use when asked to verify, validate, test, or prove that a Beacon change works for real rather than just compiling; when asked whether telemetry, event capture, commands, file paths, prompts, tokens, or approvals are still recorded correctly; when investigating a suspected capture gap; or when preparing a Beacon pull request","version":1,"lift":{"pass_rate_delta_pts":61.9,"pass_rate_pct":78.3,"total_cases":23,"passed_cases":18,"tokens_delta_pct":7,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-10-10T21:52:13.016467+00:00"},"skill_score":0.8571000000000001,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":61.9,"with_pass_pct":85.7,"without_pass_pct":23.8,"tokens_delta_pct":7,"turns_delta_pct":0,"total_cases":23,"cases_aggregated":21,"verdict":"mixed","never_hurt":true,"completed_at":"2026-10-10T21:52:13.016467+00:00","run_id":"0c2cb6a3-ecdf-407d-ab7b-f93a2850b528","latest_attempt":{"id":"0c2cb6a3-ecdf-407d-ab7b-f93a2850b528","runner_model":"gemini-3.6-flash","overall_verdict":"mixed","completed_at":"2026-10-10T21:52:13.016467+00:00","gate":null},"version_number":1,"is_latest_version":true,"gate":null}],"trust":{"skill_safety":"passed","safety_status":"clean","intent_verdict":"safe","content_status":"clean","indexable":true},"license":"MIT","install_count":0,"total_uses":0,"total_users":0,"manifest_hash":"a761d3e8d5caf76e0cfe4ec6ad0bf6aa5deb36a1d958d6fc8cc368de38276e84","install_name":"asymptote-labs-self-verify-beacon-in-sandbox","version_id":"a7006658-6cce-4971-9f1a-48503162208e","body_sha256":"a761d3e8d5caf76e0cfe4ec6ad0bf6aa5deb36a1d958d6fc8cc368de38276e84","render_hash":"84a44d4702d783e9537ff86fd7ac4cb362aa428e43515fcd88a7407ddef98b3d","raw_url":"https://app.decimal.ai/s/asymptote-labs-self-verify-beacon-in-sandbox/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/asymptote-labs-self-verify-beacon-in-sandbox"}