{ "run_id": "TayHCode--search-first-claude-haiku-5-5-1792607402277902526", "date": "2026-10-21T18:33:24.562693+00:00", "repo": "TayHCode/search-first", "kind": "mcp", "source": "https://github.com/TayHCode/search-first", "commit": "2b7c5fd54b96bdd2a736eb2ae25db35d2cb71d7d", "model": "claude-haiku-5-5", "model_version": "claude-haiku-5-5", "test_version": "readme-b08aaa568d9005099b995fc51d01450b15d399d9445aa4d6f554b73c4f2218b9", "pass": true, "outcome": "pass", "time_to_working_s": 149.528951151995, "total_s": 202.28470849990845, "steps": [ "uname -a; id -u; cat /etc/os-release 2>/dev/null | head -3; cd && pwd && ls -la && git status 2>&1 | head -2", "cd && cat README.md 2>/dev/null | head -300", "cd && sed -n 300,600p README.md | grep -v '^$' | head -220; echo ---; ls .coldpass; cat AGENTS.md; echo ---; /opt/homebrew/bin/python3 --version; which uv uvx; ls scripts; cat scripts/check_python.py | head -40", "cd && git init -q && git remote add origin https://github.com/TayHCode/search-first.git && (git fetch --depth 1 origin 2b7c5fd54b96bdd2a736eb2ae25db35d2cb71d7d 2>&1 | tail -3); git reset --mixed FETCH_HEAD 2>&1 | tail -2; git log --oneline -1 2>&1; echo ---; mkdir -p \"$HOME/uv-bin\" && curl -LsSf https://astral.sh/uv/install.sh | UV_INSTALL_DIR=\"$HOME/uv-bin\" UV_NO_MODIFY_PATH=1 sh 2>&1 | tail -3; \"$HOME/uv-bin/uv\" --version", "cd && echo $HOME && UVX=\"$HOME/uv-bin/uvx\"; \"$UVX\" --python 3.12 --from . search-first --help 2>&1 | tail -40; echo \"rc=${PIPESTATUS[0]}\"", "cd && grep -n '^#' README.md; echo ---; sed -n '/^## Proof and development/,/^## [A-Z]/p' README.md | head -80; echo ---; env | grep -i -E 'token|proxy' | sed 's/=.*/=/'; curl -sS -m 10 -o /dev/null -w '%{http_code}\\n' https://api.github.com/rate_limit", "cd && UV=\"$HOME/uv-bin/uv\"; \"$UV\" sync --locked --extra dev --python 3.12 2>&1 | tail -5; echo \"sync rc=${PIPESTATUS[0]}\"; timeout 600 \"$UV\" run --locked pytest -q 2>&1 | tail -8; echo \"pytest rc=${PIPESTATUS[0]}\"", "cd && UV=\"$HOME/uv-bin/uv\"; \"$UV\" run --locked pytest -q 2>&1 | tail -8; echo \"pytest rc=${PIPESTATUS[0]}\"; \"$UV\" run --locked ruff check . 2>&1 | tail -2; echo \"ruff rc=${PIPESTATUS[0]}\"", "mkdir -p && cat > <<'EOF'\nimport asyncio, json, sys\nfrom mcp import ClientSession, StdioServerParameters\nfrom mcp.client.stdio import stdio_client\nUVX = \"\"\nasync def main():\n params = StdioServerParameters(command=sys.argv[1], args=sys.argv[2:])\n async with stdio_client(params) as (r, w):\n async with ClientSession(r, w) as s:\n await s.initialize()\n tools = await s.list_tools()\n print(\"TOOLS:\", [t.name for t in tools.tools])\n res = await s.call_tool(\"search_existing\", {\n \"idea\": \"a terminal tool that closes idle browser tabs automatically\",\n \"queries\": [\"chrome idle tabs\", \"close inactive tabs\"],\n \"limit\": 3})\n for c in res.content:\n print(c.text[:1500])\nasyncio.run(main())\nEOF\nln -sf \"$HOME/uv-bin/uvx\" ; cd && -I --python 3.12 --from search-first 2>&1 | tail -60", "rm -f ; cd && -I --python 3.12 --from search-first 2>&1 | tail -40", "ls -la ; cd && -I --python 3.12 --from search-first 2>&1 | tail -40", "cd && grep -rn -i -E 'cron|schedul|--once|--now|while True|sleep\\(|webhook' src pyproject.toml | head; echo \"grep rc=$?\"; UV=\"\"; \"$UV\" run --locked mypy 2>&1 | tail -2; echo \"mypy rc=${PIPESTATUS[0]}\"; \"$UV\" run --locked ruff format --check . 2>&1 | tail -1; echo \"fmt rc=${PIPESTATUS[0]}\"; \"$UV\" run --locked python -m build --outdir 2>&1 | tail -2; echo \"build rc=${PIPESTATUS[0]}\"", "cd && sed -n 40,60p src/search_first/discovery.py; grep -n 'def main\\|add_argument' src/search_first/*.py | head -30", "cat > <<'EOF'\nimport asyncio, sys\nfrom mcp import ClientSession, StdioServerParameters\nfrom mcp.client.stdio import stdio_client\nasync def main():\n async with stdio_client(StdioServerParameters(command=sys.argv[1], args=sys.argv[2:])) as (r, w):\n async with ClientSession(r, w) as s:\n await s.initialize()\n res = await s.call_tool(\"inspect_repo\", {\"repo\": \"TayHCode/search-first\"})\n for c in res.content:\n print(c.text[:700])\nasyncio.run(main())\nEOF\ncd && -I --python 3.12 --from search-first 2>&1 | grep -v '^HTTP' | tail -30", "cd && grep -c \"An MCP server that discovers existing public projects, explains a ranked shortlist,\" README.md; grep -c \"README excerpt, SPDX license/name, size in KB, up to five last commits, open issue\" README.md; grep -c \"Accepts \\`owner/repo\\` or\" README.md; grep -c \"All automated tests use recorded public fixtures\" README.md; grep -c \"uv run --locked pytest -q\" README.md\ncat > .coldpass/probe.json <<'EOF'\n{\"kind\":\"mcp\",\"argv\":[\"\",\"--python\",\"3.12\",\"--from\",\"\",\"search-first\"],\"cwd\":\"\",\"tool\":\"search_existing\",\"arguments\":{\"idea\":\"a terminal tool that closes idle browser tabs automatically\",\"queries\":[\"chrome idle tabs\",\"close inactive tabs\"],\"limit\":3},\"expected_text\":\"TayHCode/cdpidletabs\"}\nEOF\ncat > .coldpass/claims.json <<'EOF'\n[\n {\"kind\":\"claim\",\"claim\":\"search_existing discovers existing public GitHub projects and returns a ranked shortlist with a verdict for an idea\",\"source\":\"An MCP server that discovers existing public projects, explains a ranked shortlist,\",\"input\":\"idea: a terminal tool that closes idle browser tabs automatically; queries chrome idle tabs and close inactive tabs; limit 3\",\"expected\":\"JSON containing a verdict and candidates ranked from GitHub search, including TayHCode/cdpidletabs\",\"probe_kind\":\"mcp\",\"argv\":[\"\",\"--python\",\"3.12\",\"--from\",\"\",\"search-first\"],\"tool\":\"search_existing\",\"arguments\":{\"idea\":\"a terminal tool that closes idle browser tabs automatically\",\"queries\":[\"chrome idle tabs\",\"close inactive tabs\"],\"limit\":3},\"expected_text\":\"TayHCode/cdpidletabs\",\"cwd\":\"\"},\n {\"kind\":\"claim\",\"claim\":\"inspect_repo returns the SPDX license and name of a public repository\",\"source\":\"README excerpt, SPDX license/name, size in KB, up to five last commits, open issue\",\"input\":\"repo: TayHCode/search-first\",\"expected\":\"JSON with license_name MIT License for TayHCode/search-first\",\"probe_kind\":\"mcp\",\"argv\":[\"\",\"--python\",\"3.12\",\"--from\",\"\",\"search-first\"],\"tool\":\"inspect_repo\",\"arguments\":{\"repo\":\"TayHCode/search-first\"},\"expected_text\":\"MIT License\",\"cwd\":\"\"}\n]\nEOF\ncat > .coldpass/examples.json <<'EOF'\n[\n {\"kind\":\"example\",\"claim\":\"Automated test suite passes using the documented locked dev environment\",\"source\":\"README.md#proof-and-development\",\"input\":\"uv run --locked pytest -q\",\"expected\":\"all tests pass\",\"argv\":[\"\",\"run\",\"--locked\",\"pytest\",\"-q\"],\"cwd\":\"\",\"expected_text\":\"201 passed\"},\n {\"kind\":\"example\",\"claim\":\"Ruff lint check passes on the repository\",\"source\":\"README.md#proof-and-development\",\"input\":\"uv run --locked ruff check .\",\"expected\":\"no lint findings\",\"argv\":[\"\",\"run\",\"--locked\",\"ruff\",\"check\",\".\"],\"cwd\":\"\",\"expected_text\":\"All checks passed!\"},\n {\"kind\":\"example\",\"claim\":\"Type check passes on the source\",\"source\":\"README.md#proof-and-development\",\"input\":\"uv run --locked mypy\",\"expected\":\"no type errors\",\"argv\":[\"\",\"run\",\"--locked\",\"mypy\"],\"cwd\":\"\",\"expected_text\":\"Success: no issues found in 7 source files\"}\n]\nEOF\ncat > .coldpass/cycles.json <<'EOF'\n{\"detected\":false,\"reason\":\"Entry points inspected: src/search_first/server.py main() runs a stdio or streamable-http MCP server on demand with no cron, scheduler, --once/--now, or webhook; the only while True loop (discovery.py clean_untrusted_text) strips HTML comments; ranking.py mentions 'schedule' only as a search keyword. The product runs as a request-driven MCP server, so there is no product cycle.\",\"checks\":[]}\nEOF\nfor f in probe claims examples cycles; do -I -c \"import json,sys;json.load(open('.coldpass/$f.json'));print('$f ok')\"; done; ls -la .coldpass", "cd && COLDPASS_WORKSPACE= /opt/homebrew/bin/python3 -I --validate --replay 2>&1 | tail -80; echo \"rc=${PIPESTATUS[0]}\"", "cd && rm -rf && cat > .coldpass/report.json <<'EOF'\n{\"outcome\":\"working\",\"fault_owner\":null,\"operation\":\"Start the search-first MCP server over stdio with the README uvx command and call search_existing (and inspect_repo) to get a real ranked GitHub shortlist for an idea\",\"operation_scope\":\"Unauthenticated (no GITHUB_TOKEN): 2 search variants per call, public GitHub only, live network to api.github.com; Python 3.12 downloaded by uv; macOS arm64 guest. Not tested: Streamable HTTP with auth, Claude Desktop/Code, and token-authenticated searches.\",\"steps\":[\"git init; git remote add origin https://github.com/TayHCode/search-first.git; git fetch --depth 1 origin 2b7c5fd54b96bdd2a736eb2ae25db35d2cb71d7d; git reset --mixed FETCH_HEAD\",\"curl -LsSf https://astral.sh/uv/install.sh | UV_INSTALL_DIR=\\\"$HOME/uv-bin\\\" UV_NO_MODIFY_PATH=1 sh\",\"uvx --python 3.12 --from . search-first --help\",\"uv sync --locked --extra dev --python 3.12\",\"uv run --locked pytest -q\",\"uv run --locked ruff check .\",\"uv run --locked ruff format --check .\",\"uv run --locked mypy\",\"uv run --locked python -m build\",\"uvx --python 3.12 --from . search-first (stdio MCP server, exercised via an MCP client calling search_existing and inspect_repo)\"],\"deviations\":[\"Guest is macOS arm64 (Darwin), not Linux; the README's macOS uvx route was used.\",\"uv was not installed in the guest, so the README's official uv installer was run with UV_INSTALL_DIR in a user-local folder ($HOME/uv-bin, which is ) and UV_NO_MODIFY_PATH=1. uv 0.13.4 installed.\",\"Workspace was not a git repo; git init and the pinned fetch/reset were run as the task instructed. The fetch succeeded.\",\"The Homebrew python3 is 3.14.8 (meets the 3.11 minimum), so the pip/venv route was not needed; uv used its own downloaded Python 3.12.\",\"First attempt to run the MCP client failed because I symlinked uvx to another folder (uv could not find its sibling uv binary). Fixed by using the real absolute uvx path. This was my setup error, not a product fault.\",\"Shell 'timeout' command is absent on this macOS guest; the pytest run was done without it.\",\"The uv sync created a .venv inside the checkout (documented development install).\"],\"stuck_step\":null,\"main_blocker\":null,\"plain_failure\":null,\"suggested_fix\":\"None needed for this guest. For more complete searches, set GITHUB_TOKEN (README 'GitHub limits and authentication'); unauthenticated results can be marked inconclusive because of the 2-variant budget and the verdict's terminal-tool constraint, which is the product working as documented.\"}\nEOF\n -I -c \"import json;json.load(open('.coldpass/report.json'));print('report ok')\"; ls -la | head -30; ls ; ps aux | grep -c '[s]earch-first'", "ps aux | grep '[s]earch-first' | cut -c1-200" ], "stuck_step": null, "error_excerpt": null, "what_it_did": "Start the search-first MCP server over stdio with the README uvx command and call search_existing (and inspect_repo) to get a real ranked GitHub shortlist for an idea", "suggested_fix": null, "tokens_in": 526031, "tokens_out": 14557, "cost_usd": 0.0219081, "usage_complete": true, "checks": [ { "check": "operation", "status": "PASS", "details": { "working": true, "argv": [ "", "--python", "3.12", "--from", "", "search-first" ], "kind": "mcp", "serverInfo": { "name": "search-first", "version": "0.1.0" }, "tools": [ "search_existing", "inspect_repo", "compare_candidates" ], "tool_schema_bytes": 4129, "tool_result": { "content": [ { "text": "{\n \"verdict\": {\n \"closest_match\": {\n \"name\": \"TayHCode/cdpidletabs\",\n \"url\": \"https://github.com/TayHCode/cdpidletabs\"\n },\n \"plausible_candidates\": 0,\n \"adjacent_candidates\": 60,\n \"recommendation\": \"inconclusive\",\n \"reasoning\": \"Required behavior or constraints are unverified: terminal. Inspect README and test those requirements; broaden queries before choosing a base. None of these is a terminal tool according to retrieved metadata in the top relevance group; terminal/CLI support is unverified. tied with 18 ; TayHCode/cdpidletabs wins by more recent push.\",\n \"provisional\": true,\n \"search_complete\": true\n },\n \"warnings\": [],\n \"candidates\": [\n {\n \"name\": \"TayHCode/cdpidletabs\",\n \"url\": \"https://github.com/TayHCode/cdpidletabs\",\n \"stars\": 0,\n \"last_push\": \"2026-10-15T16:44:40Z\",\n \"license\": \"MIT\",\n \"relevance_score\": 0.54,\n \"idea_term_coverage\": 1.0,\n \"missing_key_terms\": [],\n \"missing_constraints\": [\n \"terminal\"\n ],\n \"why_it_matched\": \"Strong core match; Core terms: 4/4 (browser, close, idle, tab); 0 stars, push 6 days ago; returned by 1 query variant(s), best GitHub rank 27. Cautions: reuse floor unverified: needs at least 25 stars and a push within 365 days; hard constraints unverified: terminal. tied with 18 ; Ta\"\n },\n {\n \"name\": \"RealUnfazed/Chrome-TabTidy\",\n \"url\": \"https://github.com/RealUnfazed/Chrome-TabTidy\",\n \"stars\": 0,\n \"last_push\": \"2026-09-28T10:41:29Z\",\n \"license\": \"MIT\",\n \"relevance_score\": 0.54,\n \"idea_term_coverage\": 1.0,\n \"missing_key_terms\": [],\n \"missing_constraints\": [\n \"terminal\"\n ],\n \"why_it_matched\": \"Strong core match; Core terms: 4/4 (browser, close, idle, tab); 0 stars, push 23 days ago; returned by 1 query variant(s), best GitHub rank 20. Cautions: reuse floor unverified: needs at least 25 stars and a push within 365 days; hard constraints unverified: terminal. tied with 18 ; T\"\n },\n {\n \"name\": \"vladbulyukhin/tab-reaper\",\n \"url\": \"https://github.com/vladbulyukhin/tab-reaper\",\n \"stars\": 2,\n \"last_push\": \"2026-09-06T19:31:45Z\",\n \"license\": \"MPL-2.0\",\n \"relevance_score\": 0.54,\n \"idea_term_coverage\": 1.0,\n \"missing_key_terms\": [],\n \"missing_constraints\": [\n \"terminal\"\n ],\n \"why_it_matched\": \"Strong core match; Core terms: 4/4 (browser, close, idle, tab); 2 stars, push 44 days ago; returned by 1 query variant(s), best GitHub rank 24. Cautions: reuse floor unverified: needs at least 25 stars and a push within 365 days; hard constraints unverified: terminal. tied with 18 ; T\"\n }\n ],\n \"unique_candidates_evaluated\": 60,\n \"errors\": [],\n \"message\": null,\n \"retry_after_seconds\": null,\n \"coverage\": {\n \"bounded\": true,\n \"truncated\": true,\n \"repositories_per_query\": 30,\n \"queries_completed\": 2,\n \"queries_failed\": 0,\n \"queries_skipped\": 1,\n \"query_budget\": 2,\n \"bounded_plan_complete\": true,\n \"results_skipped\": 57,\n \"unretrieved_results\": null,\n \"note\": \"Counts refer to deduplicated retrieved projects, not all of GitHub. Metadata-only lexical ranking; no candidate has been run or tested.\"\n },\n \"notes\": [\n \"Unauthenticated mode: at most 2 search variants per call; set GITHUB_TOKEN for complete searches. Shared-IP quota still applies.\"\n ]\n}", "type": "text" } ], "isError": false, "structuredContent": { "verdict": { "closest_match": { "name": "TayHCode/cdpidletabs", "url": "https://github.com/TayHCode/cdpidletabs" }, "plausible_candidates": 0, "adjacent_candidates": 60, "recommendation": "inconclusive", "reasoning": "Required behavior or constraints are unverified: terminal. Inspect README and test those requirements; broaden queries before choosing a base. None of these is a terminal tool according to retrieved metadata in the top relevance group; terminal/CLI support is unverified. tied with 18 ; TayHCode/cdpidletabs wins by more recent push.", "provisional": true, "search_complete": true }, "warnings": [], "candidates": [ { "name": "TayHCode/cdpidletabs", "url": "https://github.com/TayHCode/cdpidletabs", "stars": 0, "last_push": "2026-10-15T16:44:40Z", "license": "MIT", "relevance_score": 0.54, "idea_term_coverage": 1.0, "missing_key_terms": [], "missing_constraints": [ "terminal" ], "why_it_matched": "Strong core match; Core terms: 4/4 (browser, close, idle, tab); 0 stars, push 6 days ago; returned by 1 query variant(s), best GitHub rank 27. Cautions: reuse floor unverified: needs at least 25 stars and a push within 365 days; hard constraints unverified: terminal. tied with 18 ; Ta" }, { "name": "RealUnfazed/Chrome-TabTidy", "url": "https://github.com/RealUnfazed/Chrome-TabTidy", "stars": 0, "last_push": "2026-09-28T10:41:29Z", "license": "MIT", "relevance_score": 0.54, "idea_term_coverage": 1.0, "missing_key_terms": [], "missing_constraints": [ "terminal" ], "why_it_matched": "Strong core match; Core terms: 4/4 (browser, close, idle, tab); 0 stars, push 23 days ago; returned by 1 query variant(s), best GitHub rank 20. Cautions: reuse floor unverified: needs at least 25 stars and a push within 365 days; hard constraints unverified: terminal. tied with 18 ; T" }, { "name": "vladbulyukhin/tab-reaper", "url": "https://github.com/vladbulyukhin/tab-reaper", "stars": 2, "last_push": "2026-09-06T19:31:45Z", "license": "MPL-2.0", "relevance_score": 0.54, "idea_term_coverage": 1.0, "missing_key_terms": [], "missing_constraints": [ "terminal" ], "why_it_matched": "Strong core match; Core terms: 4/4 (browser, close, idle, tab); 2 stars, push 44 days ago; returned by 1 query variant(s), best GitHub rank 24. Cautions: reuse floor unverified: needs at least 25 stars and a push within 365 days; hard constraints unverified: terminal. tied with 18 ; T" } ], "unique_candidates_evaluated": 60, "errors": [], "message": null, "retry_after_seconds": null, "coverage": { "bounded": true, "truncated": true, "repositories_per_query": 30, "queries_completed": 2, "queries_failed": 0, "queries_skipped": 1, "query_budget": 2, "bounded_plan_complete": true, "results_skipped": 57, "unretrieved_results": null, "note": "Counts refer to deduplicated retrieved projects, not all of GitHub. Metadata-only lexical ranking; no candidate has been run or tested." }, "notes": [ "Unauthenticated mode: at most 2 search variants per call; set GITHUB_TOKEN for complete searches. Shared-IP quota still applies." ] } }, "tool_result_checked": true, "scope": "product operation" } } ], "safety": { "version": "z2x-1", "rules_version": "z2x-1", "summary": "Review signals: 2 known vulnerability.", "findings": [ { "kind": "known-vulnerability", "count": 2, "note": "OSV reports a known vulnerability in this dependency version.", "location_count": 1, "path": "certifi" } ], "context": [], "limitations": [ "A short run cannot establish that code is safe.", "Connections show IP addresses; proxies can hide the final hostname.", "Tracing covers dispatched commands and their children, not the whole OS; guest root can interfere with tracing.", "macos behavior observation needs an OS-native file/network/process collector; only the static scan ran.", "No Linux syscall trace was collected." ], "static": { "dependency_note": "OSV scanned supported lockfiles; unpinned dependencies and unsupported formats are outside this check." }, "evidence_url": "/safety/?run=TayHCode--search-first-claude-haiku-5-5-1792607402277902526", "evidence_file": "/data/safety/TayHCode--search-first-claude-haiku-5-5-1792607402277902526.json.gz" }, "agent_execution": "native_agent", "agent_runtime": "claude-code", "agent_runtime_version": "2.1.300 (Claude Code)", "tool_transport": "mcp-assigned-vm", "platform": "macos", "reasoning": "low", "service_tier": null, "resources": { "cpus": null, "memory_mib": 4096, "disk_mib": 32768 }, "native_tool_calls": 18, "native_bundle": null, "architecture": null, "backend": "tart", "platform_details": { "backend": "tart", "os": "macos" }, "platform_conflicts": null, "sandbox_source": null, "source_pin": { "commit": "2b7c5fd54b96bdd2a736eb2ae25db35d2cb71d7d", "url": "https://github.com/TayHCode/search-first" }, "purpose": "initial", "profile": { "model": "claude-haiku-5-5", "reasoning": "low" }, "fault": { "owner": null, "status": "resolved", "reason": null }, "fix_id": null, "verifies_run_id": null, "hosting": null, "operation_scope": "product operation", "tool_calls": 18, "guest_setup": null, "runtime": null, "runtime_version": null, "runtime_revision": null, "source_revision": null, "evidence_version": null, "failure_origin": null, "evidence_strength": "readme_checked", "works": "yes", "install_s": null, "first_use_s": null, "mcp": "local", "needs": [], "needs_which": null, "agent_interface": [ "mcp" ], "license": "MIT", "repo_url": "https://github.com/TayHCode/search-first", "cost_to_try": "free", "hardware": null, "what_failed": null, "local_or_hosted": "local", "cycle_checks": [ { "kind": "cycle", "claim": "Scheduled or looping main behavior", "source": "repository entry points", "input": "source inspection", "expected": "identify the product trigger", "verdict": "yes", "outcome": "Entry points inspected: src/search_first/server.py main() runs a stdio or streamable-http MCP server on demand with no cron, scheduler, --once/--now, or webhook; the only while True loop (discovery.py clean_untrusted_text) strips HTML comments; ranking.py mentions 'schedule' only as a search keyword. The product runs as a request-driven MCP server, so there is no product cycle.", "evidence": "Entry points inspected: src/search_first/server.py main() runs a stdio or streamable-http MCP server on demand with no cron, scheduler, --once/--now, or webhook; the only while True loop (discovery.py clean_untrusted_text) strips HTML comments; ranking.py mentions 'schedule' only as a search keyword. The product runs as a request-driven MCP server, so there is no product cycle.", "command": "" } ], "claims": [ { "kind": "claim", "claim": "search_existing discovers existing public GitHub projects and returns a ranked shortlist with a verdict for an idea", "source": "An MCP server that discovers existing public projects, explains a ranked shortlist,", "input": "{\"tool\": \"search_existing\", \"arguments\": {\"idea\": \"a terminal tool that closes idle browser tabs automatically\", \"queries\": [\"chrome idle tabs\", \"close inactive tabs\"], \"limit\": 3}}", "expected": "JSON containing a verdict and candidates ranked from GitHub search, including TayHCode/cdpidletabs", "command": " --python 3.12 --from search-first tools/call {\"tool\": \"search_existing\", \"arguments\": {\"idea\": \"a terminal tool that closes idle browser tabs automatically\", \"queries\": [\"chrome idle tabs\", \"close inactive tabs\"], \"limit\": 3}}", "verdict": "yes", "outcome": "Real input produced the expected result: TayHCode/cdpidletabs", "evidence": "TayHCode/cdpidletabs\\\",\\n \\\"url\\\": \\\"https://github.com/TayHCode/cdpidletabs\\\"\\n },\\n \\\"plausible_candidates\\\": 0,\\n \\\"adjacent_candidates\\\": 60,\\n \\\"recommendation\\\": \\\"inconclusive\\\",\\n \\\"reasoning\\\": \\\"Required behavior or constraints are unverified: terminal. Inspect README and test those requirements; broaden queries before choosing a base. None of these is a terminal tool according to retrieved metadata in the top relevance group; terminal/CLI support is unverified. tied with 18 ; TayHCode/cdpidletabs wins by more recent push.\\\",\\n \\\"provisional\\\": t", "source_checked": true, "source_file": "README.md" }, { "kind": "claim", "claim": "inspect_repo returns the SPDX license and name of a public repository", "source": "README excerpt, SPDX license/name, size in KB, up to five last commits, open issue", "input": "{\"tool\": \"inspect_repo\", \"arguments\": {\"repo\": \"TayHCode/search-first\"}}", "expected": "JSON with license_name MIT License for TayHCode/search-first", "command": " --python 3.12 --from search-first tools/call {\"tool\": \"inspect_repo\", \"arguments\": {\"repo\": \"TayHCode/search-first\"}}", "verdict": "yes", "outcome": "Real input produced the expected result: MIT License", "evidence": "MIT License\\\",\\n \\\"language\\\": \\\"Python\\\",\\n \\\"topics\\\": [\\n \\\"mcp\\\",\\n \\\"python\\\"\\n ],\\n \\\"size_kb\\\": 222,\\n \\\"notes\\\": [\\n \\\"Unauthenticated mode: at most 2 search variants per call; set GITHUB_TOKEN for complete searches. Shared-IP quota still applies.\\\"\\n ],\\n \\\"readme_excerpt\\\": \\\"# search-first\\\\n\\\\n**Before you build this, here is what already exists on GitHub.**\\\\n\\\\nAn MCP server that discovers existing public projects, explains a ranked shortlist,\\\\ninspects maintenance and reuse signals, and compares candidates. Search first,\\\\ninspect and test a candidate, then use ", "source_checked": true, "source_file": "README.md" } ], "claims_note": null, "example_checks": [ { "kind": "example", "claim": "Automated test suite passes using the documented locked dev environment", "source": "README.md#proof-and-development", "input": "uv run --locked pytest -q", "command": " run --locked pytest -q", "evidence": "........................................................................ [ 35%]\n........................................................................ [ 71%]\n......................................................... [100%]\n201 passed in 1.60s", "deferred": false, "expected": "all tests pass", "returncode": 0, "verdict": "yes", "outcome": "command completed successfully" }, { "kind": "example", "claim": "Ruff lint check passes on the repository", "source": "README.md#proof-and-development", "input": "uv run --locked ruff check .", "command": " run --locked ruff check .", "evidence": "All checks passed!", "deferred": false, "expected": "no lint findings", "returncode": 0, "verdict": "yes", "outcome": "command completed successfully" }, { "kind": "example", "claim": "Type check passes on the source", "source": "README.md#proof-and-development", "input": "uv run --locked mypy", "command": " run --locked mypy", "evidence": "Success: no issues found in 7 source files", "deferred": false, "expected": "no type errors", "returncode": 0, "verdict": "yes", "outcome": "command completed successfully" } ], "does_what_it_says": "yes", "maintenance": { "archived": false, "commits_90d": 9, "last_commit_at": "2026-10-15T16:25:15Z", "last_release_at": null, "median_reply_hours": null, "merged_prs_90d": 2, "note": "actively maintained: last commit 6 days ago; 9 commits and 2 merged PRs in 90 days; 0 open issues, 0 open PRs; no releases", "open_issues": 0, "open_prs": 0, "reply_share": null, "reply_threads": 0, "verdict": "maintained" }, "maintenance_verdict": "maintained", "maintenance_note": "actively maintained: last commit 6 days ago; 9 commits and 2 merged PRs in 90 days; 0 open issues, 0 open PRs; no releases", "maintained": "active", "maintained_note": "last commit 6 days ago", "last_commit_at": "2026-10-15T16:44:45Z", "last_release_at": null, "open_issues": null, "answered_issues": null, "platforms_claimed": [ "linux", "mac", "windows" ], "topic": "mcp-server", "agent_interfaces": [ { "interface": "mcp", "evidence": "independent checker", "observed": true, "operation_checked": true } ], "agent_interfaces_note": "README metadata is a discovery hint, not pinned documentation proof. Observed interfaces were exercised in this run. An empty list means unknown.", "mcp_context": { "tool_count": 3, "schema_bytes": 4129, "tokens_approx": 1033, "estimate_method": "ceil(compact UTF-8 tools/list JSON bytes / 4)", "scope": "returned tools/list page only; excludes client framing and tool results" }, "tested_at": "2026-10-21T18:33:24.562693+00:00", "tested_commit": "2b7c5fd54b96bdd2a736eb2ae25db35d2cb71d7d", "tested_with": { "agent": "claude-code", "agent_version": "2.1.300 (Claude Code)", "model": "claude-haiku-5-5", "model_route": "claude-haiku-5-5", "reasoning": "low", "os": "macos", "backend": "tart", "transport": "mcp-assigned-vm" }, "setup_identity": { "repo": "TayHCode/search-first", "source": "https://github.com/TayHCode/search-first", "commit": "2b7c5fd54b96bdd2a736eb2ae25db35d2cb71d7d", "source_revision": null, "os": "mac", "architecture": null, "backend": "tart", "model": "claude-haiku-5-5", "model_version": "claude-haiku-5-5", "agent_execution": "native_agent", "agent_runtime": "claude-code", "agent_runtime_version": "2.1.300 (Claude Code)", "tool_transport": "mcp-assigned-vm", "runtime": null, "runtime_version": null, "runtime_revision": null, "sandbox_source": null, "guest_setup": null, "source_pin": { "commit": "2b7c5fd54b96bdd2a736eb2ae25db35d2cb71d7d", "url": "https://github.com/TayHCode/search-first" }, "platform_details": { "os": "macos", "backend": "tart" }, "platform_conflicts": null, "reasoning": "low", "service_tier": null, "resources": { "cpus": null, "memory_mib": 4096, "disk_mib": 32768 }, "operation": "Start the search-first MCP server over stdio with the README uvx command and call search_existing (and inspect_repo) to get a real ranked GitHub shortlist for an idea", "operation_scope": "product operation", "hosting": null, "kind": "mcp", "test_version": "readme-b08aaa568d9005099b995fc51d01450b15d399d9445aa4d6f554b73c4f2218b9", "evidence_version": null }, "other_model": null, "other_run_id": null, "models_agree": null, "furthest_model": null, "transcript_url": "/transcripts/TayHCode--search-first-claude-haiku-5-5-1792607402277902526.txt", "report_url": "/reports/TayHCode--search-first-claude-haiku-5-5-1792607402277902526.json" }