{ "run_id": "TayHCode--agentlocker-claude-haiku-5-5-1792726492363212688", "checker": { "claims": [ { "claim": "Find a skill in agentlocker, read its supporting files, and use it for my task.", "command": "python3 mcp_endpoint.py tools/call {\"tool\": \"hub_get_item\", \"arguments\": {\"kind\": \"skill\", \"name\": \"minimal-diff-review\"}}", "evidence": "Review a proposed diff for correctness, requested scope and missing behavioral tests before handoff.\\\\n---\\\\n\\\\n# Review the diff\\\\n\\\\nRead the task, applicable project instructions and complete diff. Follow changed call sites and contracts far enough to identify observable regressions.\\\\n\\\\nCheck boundary inputs, error handling, preservation of existing data and compatibility with callers. Look for changes unrelated to the requested outcome. Ask whether tests distinguish the intended behavior from plausible failures rather than repeat the implementation.\\\\n\\\\nReport actionable findings with f", "expected": "hub_get_item returns the skill's SKILL.md text", "input": "{\"tool\": \"hub_get_item\", \"arguments\": {\"kind\": \"skill\", \"name\": \"minimal-diff-review\"}}", "kind": "claim", "outcome": "Real input produced the expected result: Review a proposed diff for correctness", "source": "Find a skill in agentlocker, read its supporting files, and use it for my task.", "source_checked": true, "source_file": "README.md", "verdict": "yes" }, { "claim": "List the routines and read one when I ask you to follow it.", "command": "python3 mcp_endpoint.py tools/call {\"tool\": \"hub_get_item\", \"arguments\": {\"kind\": \"routine\", \"name\": \"inventory-digest\"}}", "evidence": "Summarize the approved hub inventory without changes.\\\\\\\",\\\\n \\\\\\\"owner\\\\\\\": \\\\\\\"agentlocker\\\\\\\",\\\\n \\\\\\\"runner\\\\\\\": \\\\\\\"t3-scheduler\\\\\\\",\\\\n \\\\\\\"schedule\\\\\\\": {\\\\n \\\\\\\"type\\\\\\\": \\\\\\\"fixed_time\\\\\\\",\\\\n \\\\\\\"time_of_day\\\\\\\": \\\\\\\"09:00\\\\\\\",\\\\n \\\\\\\"weekdays\\\\\\\": [\\\\n 1,\\\\n 2,\\\\n 3,\\\\n 4,\\\\n 5\\\\n ]\\\\n },\\\\n \\\\\\\"timezone\\\\\\\": \\\\\\\"UTC\\\\\\\",\\\\n \\\\\\\"prompt\\\\\\\": \\\\\\\"routine-prompt.md\\\\\\\",\\\\n \\\\\\\"overlap\\\\\\\": \\\\\\\"skip\\\\\\\",\\\\n \\\\\\\"timeout_seconds\\\\\\\": 600,\\\\n \\\\\\\"enabled\\\\\\\": false\\\\n}\\\\n\\\", \\\"routines/inventory-digest/routine-prompt.md\\\": \\\"# Read-only invento", "expected": "the routine's description is returned", "input": "{\"tool\": \"hub_get_item\", \"arguments\": {\"kind\": \"routine\", \"name\": \"inventory-digest\"}}", "kind": "claim", "outcome": "Real input produced the expected result: Summarize the approved hub inventory without changes", "source": "List the routines and read one when I ask you to follow it.", "source_checked": true, "source_file": "README.md", "verdict": "yes" } ], "cycle_checks": [ { "claim": "Routine runs when its scheduler tick fires", "command": "python3 routine_runtime.py ", "evidence": "Summarize the approved hub inventory without changes.", "expected": "wrapper runs the job once and prints the prompt", "input": "job.json with prompt 'Summarize the approved hub inventory without changes.'", "kind": "cycle", "method": "run-once: invoke the wrapper by hand on a throwaway job file in with every_seconds=0 and echo as the agent command", "outcome": "Triggered one cycle by hand (run-once: invoke the wrapper by hand on a throwaway job file in with every_seconds=0 and echo as the agent command; normal trigger: local runner tick (cron/systemd/launchd call routine_runtime.py ) once a minute): Summarize the approved hub inventory without changes.", "returncode": 0, "schedule": "local runner tick (cron/systemd/launchd call routine_runtime.py ) once a minute", "source": "routine_runtime.py", "verdict": "yes" } ], "details": { "argv": [ "python3", "mcp_endpoint.py" ], "kind": "mcp", "scope": "product operation", "serverInfo": { "name": "agentlocker", "version": "1.0.0" }, "tool_result": { "content": [ { "text": "{\"kind\": \"skill\", \"name\": \"minimal-diff-review\", \"files\": {\"skills/minimal-diff-review/SKILL.md\": \"---\\nname: minimal-diff-review\\ndescription: Review a proposed diff for correctness, requested scope and missing behavioral tests before handoff.\\n---\\n\\n# Review the diff\\n\\nRead the task, applicable project instructions and complete diff. Follow changed call sites and contracts far enough to identify observable regressions.\\n\\nCheck boundary inputs, error handling, preservation of existing data and compatibility with callers. Look for changes unrelated to the requested outcome. Ask whether tests distinguish the intended behavior from plausible failures rather than repeat the implementation.\\n\\nReport actionable findings with file locations, triggering conditions and consequences. Separate confirmed defects from questions requiring evidence. If no defect is found, say so and name unverified behavior. Review alone does not authorize edits, publication or destructive actions.\\n\"}, \"omitted\": [], \"truncated\": false, \"max_bytes\": 1048576}", "type": "text" } ], "isError": false }, "tool_result_checked": true, "tool_schema_bytes": 3344, "tools": [ "hub_list_skills", "hub_list_rules", "hub_list_mcp_servers", "hub_list_routines", "hub_list_plugins", "hub_list_connections", "hub_get_item" ], "working": true }, "evidence_strength": "readme_checked", "example_checks": [ { "claim": "Contributor test suite runs (MCP endpoint module)", "command": "python3 -m unittest discover -s tests -p test_endpoint.py -v", "deferred": false, "evidence": "(test_endpoint.SkillFilesTests.test_unsafe_directory_is_omitted_without_losing_other_files) ... ok\ntest_unsafe_file_name_is_reported (test_endpoint.SkillFilesTests.test_unsafe_file_name_is_reported) ... ok\ntest_windows_newlines_match_text_reader_behavior (test_endpoint.SkillFilesTests.test_windows_newlines_match_text_reader_behavior) ... ok\ntest_initialize_prompts_resources_and_get_item_over_stdio (test_endpoint.StdioEndToEndTests.test_initialize_prompts_resources_and_get_item_over_stdio) ... ok\n\n----------------------------------------------------------------------\nRan 60 tests in 21.195s\n\nOK", "expected": "endpoint tests complete with exit 0", "input": "python3 -m unittest discover -s tests -p test_endpoint.py -v", "kind": "example", "outcome": "command completed successfully", "returncode": 0, "source": "CONTRIBUTING.md", "verdict": "yes" }, { "claim": "Local catalog proof runs", "command": "python3 examples/test-servers/local_catalog_proof.py", "deferred": false, "evidence": "rce import upgrade, not historical release migration\",\n \"no native client, provider, gateway, remote or scheduler execution\"\n ],\n \"platform\": \"linux\",\n \"product_agent_proof\": false,\n \"python\": \"3.12.3\",\n \"real_provider_proof\": false,\n \"remote_proof\": false,\n \"scheduler_proof\": false,\n \"source\": {\n \"digest_scope\": \"copied runtime/catalog files plus proof; working bytes, including local edits\",\n \"file_count\": 61,\n \"revision\": \"79049b16e04e7ab876bc3179341acb9d1766eb41\",\n \"sha256\": \"cb657eacd2733b6363a9a24694060bef6a5b21be6907c0ba7e5c2457f3a16ddb\"\n },\n \"status\": \"passed\"\n}", "expected": "proof status passed", "input": "examples/test-servers/local_catalog_proof.py", "kind": "example", "outcome": "command completed successfully", "returncode": 0, "source": "CONTRIBUTING.md", "verdict": "yes" }, { "claim": "Maintainer source check", "command": "python3 hub.py check", "deferred": false, "evidence": "PASS: manifest schema\nPASS: MIT license\nPASS: manifest content hashes\nPASS: local state ignored and untracked\nPASS: secret and private path scan\nPASS: commit emails allowlisted", "expected": "all checks pass", "input": "python3 hub.py check", "kind": "example", "outcome": "command completed successfully", "returncode": 0, "source": "CONTRIBUTING.md", "verdict": "yes" } ], "status": "PASS" }, "diagnosis": null }