{
  "run_id": "TayHCode--agentlocker-claude-haiku-5-5-1792735161240999637",
  "date": "2026-10-23T06:22:14.985857+00:00",
  "repo": "TayHCode/agentlocker",
  "kind": "mcp",
  "source": "https://github.com/TayHCode/agentlocker",
  "commit": "79049b16e04e7ab876bc3179341acb9d1766eb41",
  "model": "claude-haiku-5-5",
  "model_version": "claude-haiku-5-5",
  "test_version": "readme-bdc1b9b3c0d2673aef87e076d14084a8123ddcf09d520c1ee2e364a37c3f4bb9",
  "pass": true,
  "outcome": "pass",
  "time_to_working_s": 1269.8827414769912,
  "total_s": 1373.7448370456696,
  "steps": [
    "cd C:\\coldpass\\workspace; Get-ChildItem -Force | Select-Object Name; Get-Content README.md -TotalCount 200; C:\\coldpass\\python\\python.exe --version; git --version",
    "cd C:\\coldpass\\workspace; Get-Content docs\\install.md; Write-Output '----'; Get-Content docs\\cli.md -TotalCount 120; Write-Output '----'; Get-Command winget,choco,scoop -ErrorAction SilentlyContinue | Select-Object Name,Source; Test-Path C:\\coldpass\\python\\Scripts; Get-ChildItem C:\\coldpass",
    "cd C:\\coldpass\\workspace; & C:\\coldpass\\python\\python.exe hub.py doctor; echo \"rc=$LASTEXITCODE\"; Get-ChildItem C:\\coldpass\\workspace\\.coldpass -Force | Select-Object Name; $env:HTTPS_PROXY; $env:NODE_USE_ENV_PROXY",
    "$ErrorActionPreference='Continue'; try { $r = Invoke-WebRequest -UseBasicParsing -Uri 'https://api.github.com/repos/git-for-windows/git/releases/latest' -TimeoutSec 60; $j = $r.Content | ConvertFrom-Json; $j.assets | Where-Object { $_.name -match 'PortableGit.*64-bit\\.7z\\.exe$' } | Select-Object name,browser_download_url | Format-List } catch { \"ERR: $($_.Exception.Message)\" }; Get-ChildItem Env: | Where-Object { $_.Name -match 'PROXY' } | ForEach-Object { \"$($_.Name)=$($_.Value)\" }",
    "$ErrorActionPreference='Stop'; $d='C:\\coldpass\\tools'; New-Item -ItemType Directory -Force -Path $d | Out-Null; $url='https://github.com/git-for-windows/git/releases/download/v2.56.0.windows.3/PortableGit-2.56.0.3-64-bit.7z.exe'; try { Invoke-WebRequest -UseBasicParsing -Uri $url -OutFile \"$d\\PortableGit.exe\" -TimeoutSec 900; Start-Process -FilePath \"$d\\PortableGit.exe\" -ArgumentList '-y',\"-o$d\\git\" -Wait -NoNewWindow; & \"$d\\git\\cmd\\git.exe\" --version } catch { \"ERR: $($_.Exception.Message)\" }",
    "$env:Path = \"C:\\coldpass\\tools\\git\\cmd;C:\\coldpass\\tools\\git\\usr\\bin;\" + $env:Path; cd C:\\coldpass\\workspace; git init; git remote add origin https://github.com/TayHCode/agentlocker; git fetch --depth 1 origin 79049b16e04e7ab876bc3179341acb9d1766eb41; git reset --mixed FETCH_HEAD; git log --oneline -1; git status --short | Select-Object -First 15",
    "Test-Path C:\\coldpass\\tools\\git\\cmd\\git.exe; Get-ChildItem C:\\coldpass\\tools\\git -Force | Select-Object -First 20 Name; $G='C:\\coldpass\\tools\\git\\cmd\\git.exe'; cd C:\\coldpass\\workspace; & $G init 2>&1; & $G remote add origin https://github.com/TayHCode/agentlocker 2>&1; & $G fetch --depth 1 origin 79049b16e04e7ab876bc3179341acb9d1766eb41 2>&1; & $G reset --mixed FETCH_HEAD 2>&1; & $G log --oneline -1 2>&1; & $G status --short 2>&1 | Select-Object -First 15",
    "Get-ChildItem Env: | Where-Object { $_.Name -like 'GIT_*' } | ForEach-Object { \"$($_.Name)=$($_.Value)\" }; [Environment]::GetEnvironmentVariable('GIT_CONFIG_COUNT','User'); [Environment]::GetEnvironmentVariable('GIT_CONFIG_COUNT','Machine')",
    "$env:GIT_CONFIG_COUNT='3'; $G='C:\\coldpass\\tools\\git\\cmd\\git.exe'; cd C:\\coldpass\\workspace; & $G init 2>&1; & $G remote add origin https://github.com/TayHCode/agentlocker 2>&1; & $G fetch --depth 1 origin 79049b16e04e7ab876bc3179341acb9d1766eb41 2>&1; & $G reset --mixed FETCH_HEAD 2>&1; & $G log --oneline -1 2>&1; & $G status --short 2>&1 | Select-Object -First 15",
    "$env:Path = 'C:\\coldpass\\tools\\git\\cmd;' + $env:Path; $env:GIT_CONFIG_COUNT='3'; cd C:\\coldpass\\workspace; & C:\\coldpass\\python\\python.exe hub.py doctor; echo \"rc=$LASTEXITCODE\"; & C:\\coldpass\\python\\python.exe hub.py --help 2>&1 | Select-Object -First 5",
    "$env:Path = 'C:\\coldpass\\tools\\git\\cmd;' + $env:Path; $env:GIT_CONFIG_COUNT='3'; cd C:\\coldpass\\workspace; & C:\\coldpass\\python\\python.exe hub.py list 2>&1 | Select-Object -First 40; echo \"rc=$LASTEXITCODE\"; & C:\\coldpass\\python\\python.exe hub.py scan 2>&1 | Select-Object -First 40; echo \"rc=$LASTEXITCODE\"",
    "cd C:\\coldpass\\workspace; Get-Content CONTRIBUTING.md | Select-Object -First 80; Write-Output '----'; Get-Content mcp_endpoint.py | Select-Object -First 60; Write-Output '----'; Get-Content docs\\routines.md | Select-Object -First 60",
    "cd C:\\coldpass\\workspace; Select-String -Path *.py -Pattern '--once|--now|\"run\"|add_parser\\(\"run|cycle|tick' | Select-Object -First 30 | ForEach-Object { \"$($_.Filename):$($_.LineNumber): $($_.Line.Trim())\" }; Write-Output '----'; Select-String -Path docs\\routines.md,docs\\reference.md,docs\\cli.md -Pattern 'once|run' | Select-Object -First 20 | ForEach-Object { \"$($_.Filename):$($_.LineNumber): $($_.Line.Trim())\" }",
    "cd C:\\coldpass\\workspace; Select-String -Path mcp_endpoint.py -Pattern 'readline|Content-Length|stdin|def main|inputSchema|\"name\": ' | Select-Object -First 25 | ForEach-Object { \"$($_.LineNumber): $($_.Line.Trim())\" }",
    "cd C:\\coldpass\\workspace; $in = @('{\"jsonrpc\":\"2.0\",\"id\":1,\"method\":\"initialize\",\"params\":{\"protocolVersion\":\"2025-06-18\",\"capabilities\":{},\"clientInfo\":{\"name\":\"t\",\"version\":\"1\"}}}','{\"jsonrpc\":\"2.0\",\"method\":\"notifications/initialized\"}','{\"jsonrpc\":\"2.0\",\"id\":2,\"method\":\"tools/call\",\"params\":{\"name\":\"hub_list_skills\",\"arguments\":{}}}','{\"jsonrpc\":\"2.0\",\"id\":3,\"method\":\"tools/call\",\"params\":{\"name\":\"hub_get_item\",\"arguments\":{\"kind\":\"skill\",\"name\":\"hub-discover\"}}}') -join \"`n\"; $in | & C:\\coldpass\\python\\python.exe -I mcp_endpoint.py 2>&1 | Out-String -Width 4000 | ForEach-Object { $_.Substring(0, [Math]::Min(2500, $_.Length)) }",
    "cd C:\\coldpass\\workspace; $in = @('{\"jsonrpc\":\"2.0\",\"id\":1,\"method\":\"initialize\",\"params\":{\"protocolVersion\":\"2025-06-18\",\"capabilities\":{},\"clientInfo\":{\"name\":\"t\",\"version\":\"1\"}}}','{\"jsonrpc\":\"2.0\",\"method\":\"notifications/initialized\"}','{\"jsonrpc\":\"2.0\",\"id\":2,\"method\":\"tools/call\",\"params\":{\"name\":\"hub_list_skills\",\"arguments\":{}}}','{\"jsonrpc\":\"2.0\",\"id\":3,\"method\":\"tools/call\",\"params\":{\"name\":\"hub_get_item\",\"arguments\":{\"kind\":\"skill\",\"name\":\"hub-discover\"}}}') -join \"`n\"; $out = $in | & C:\\coldpass\\python\\python.exe mcp_endpoint.py 2>&1 | Out-String; $out.Substring(0,[Math]::Min(3000,$out.Length))",
    "cd C:\\coldpass\\workspace; $py='C:\\\\coldpass\\\\python\\\\python.exe'; $ws='C:\\\\coldpass\\\\workspace'; $genv=@{ PATH='C:\\coldpass\\tools\\git\\cmd;C:\\Windows\\System32;C:\\Windows'; GIT_CONFIG_COUNT='3' };\n$probe=[ordered]@{kind='mcp'; argv=@($py,'mcp_endpoint.py'); cwd=$ws; tool='hub_get_item'; arguments=[ordered]@{kind='skill';name='hub-discover'}; expected_text='Discover the hub'};\n$claims=@(\n [ordered]@{kind='claim'; claim='Ask a connected agent to find and read a skill from the library over MCP'; source='Find a skill in agentlocker, read its supporting files, and use it for my task.'; input='hub-discover skill'; expected='The MCP endpoint returns the hub-discover skill text'; probe_kind='mcp'; argv=@($py,'mcp_endpoint.py'); tool='hub_get_item'; arguments=[ordered]@{kind='skill';name='hub-discover'}; expected_text='Discover the hub'; cwd=$ws},\n [ordered]@{kind='claim'; claim='Setup needs only Python and Git, with no Python packages to install; doctor reports the installation as passing'; source='Setup needs Python and Git; no Python packages to install.'; input='python hub.py doctor'; expected='doctor prints PASS: installation state'; probe_kind='cli'; argv=@($py,'hub.py','doctor'); expected_text='PASS: installation state'; cwd=$ws; env=$genv},\n [ordered]@{kind='claim'; claim='Shipped catalog entries are listed by the list command'; source='Shipped entries are indexed in [manifest.json](manifest.json).'; input='list --kind skills'; expected='The shipped hub-discover skill is listed'; probe_kind='cli'; argv=@($py,'hub.py','list','--kind','skills'); expected_text='hub-discover'; cwd=$ws; env=$genv}\n)\n$enc=New-Object System.Text.UTF8Encoding($false)\n[IO.File]::WriteAllText(\"$ws\\.coldpass\\probe.json\", ($probe | ConvertTo-Json -Depth 10), $enc)\n[IO.File]::WriteAllText(\"$ws\\.coldpass\\claims.json\", (ConvertTo-Json -InputObject $claims -Depth 10), $enc)\nGet-Content .coldpass\\probe.json; Get-Content .coldpass\\claims.json | Select-Object -First 5",
    "cd C:\\coldpass\\workspace; $py='C:\\coldpass\\python\\python.exe'; $ws='C:\\coldpass\\workspace'; $genv=[ordered]@{ PATH='C:\\coldpass\\tools\\git\\cmd;C:\\Windows\\System32;C:\\Windows'; GIT_CONFIG_COUNT='3' };\n$probe=[ordered]@{kind='mcp'; argv=@($py,'mcp_endpoint.py'); cwd=$ws; tool='hub_get_item'; arguments=[ordered]@{kind='skill';name='hub-discover'}; expected_text='Discover the hub'};\n$claims=@(\n [ordered]@{kind='claim'; claim='Ask a connected agent to find and read a skill from the library over MCP'; source='Find a skill in agentlocker, read its supporting files, and use it for my task.'; input='hub-discover skill'; expected='The MCP endpoint returns the hub-discover skill text'; probe_kind='mcp'; argv=@($py,'mcp_endpoint.py'); tool='hub_get_item'; arguments=[ordered]@{kind='skill';name='hub-discover'}; expected_text='Discover the hub'; cwd=$ws},\n [ordered]@{kind='claim'; claim='Setup needs only Python and Git, with no Python packages to install; doctor reports the installation as passing'; source='Setup needs Python and Git; no Python packages to install.'; input='python hub.py doctor'; expected='doctor prints PASS: installation state'; probe_kind='cli'; argv=@($py,'hub.py','doctor'); expected_text='PASS: installation state'; cwd=$ws; env=$genv},\n [ordered]@{kind='claim'; claim='Shipped catalog entries are listed by the list command'; source='Shipped entries are indexed in [manifest.json](manifest.json).'; input='list --kind skills'; expected='The shipped hub-discover skill is listed'; probe_kind='cli'; argv=@($py,'hub.py','list','--kind','skills'); expected_text='hub-discover'; cwd=$ws; env=$genv}\n)\n$enc=New-Object System.Text.UTF8Encoding($false)\n[IO.File]::WriteAllText(\"$ws\\.coldpass\\probe.json\", ($probe | ConvertTo-Json -Depth 10), $enc)\n[IO.File]::WriteAllText(\"$ws\\.coldpass\\claims.json\", (ConvertTo-Json -InputObject $claims -Depth 10), $enc)\nGet-Content .coldpass\\probe.json | Select-String argv -Context 0,3",
    "$env:COLDPASS_WORKSPACE='C:\\coldpass\\workspace'; & C:\\coldpass\\python\\python.exe -I C:\\coldpass\\checker\\check.py --validate --replay 2>&1 | Out-String | ForEach-Object { $_.Substring(0,[Math]::Min(6000,$_.Length)) }; \"rc=$LASTEXITCODE\"",
    "cd C:\\coldpass\\workspace; $py='C:\\coldpass\\python\\python.exe'; $ws='C:\\coldpass\\workspace'; $genv=[ordered]@{ PATH='C:\\coldpass\\tools\\git\\cmd;C:\\Windows\\System32;C:\\Windows'; GIT_CONFIG_COUNT='3' };\n$claims=@(\n [ordered]@{kind='claim'; claim='Ask a connected agent to find and read a skill from the library over MCP'; source='Find a skill in agentlocker, read its supporting files, and use it for my task.'; input='hub-discover skill'; expected='The MCP endpoint returns the hub-discover skill text'; probe_kind='mcp'; argv=@($py,'mcp_endpoint.py'); tool='hub_get_item'; arguments=[ordered]@{kind='skill';name='hub-discover'}; expected_text='Discover the hub'; cwd=$ws},\n [ordered]@{kind='claim'; claim='Shipped catalog entries are listed by the list command'; source='Shipped entries are indexed in [manifest.json](manifest.json).'; input='list --kind skills'; expected='The shipped hub-discover skill is listed'; probe_kind='cli'; argv=@($py,'hub.py','list','--kind','skills'); expected_text='hub-discover'; cwd=$ws; env=$genv}\n)\n$enc=New-Object System.Text.UTF8Encoding($false)\n[IO.File]::WriteAllText(\"$ws\\.coldpass\\claims.json\", (ConvertTo-Json -InputObject $claims -Depth 10), $enc)\n$env:COLDPASS_WORKSPACE='C:\\coldpass\\workspace'; & C:\\coldpass\\python\\python.exe -I C:\\coldpass\\checker\\check.py --validate --replay 2>&1 | Out-String | ForEach-Object { $_.Substring(0,[Math]::Min(1200,$_.Length)) }; \"rc=$LASTEXITCODE\"",
    "$ErrorActionPreference='Continue'; cd C:\\coldpass\\workspace; & C:\\coldpass\\python\\python.exe -m venv C:\\coldpass\\venv 2>&1; & C:\\coldpass\\venv\\Scripts\\python.exe -m pip install pillow==13.0.0 tzdata==2026.5 2>&1 | Select-Object -Last 4; & C:\\coldpass\\venv\\Scripts\\python.exe --version; Get-ChildItem examples\\test-servers -Force | Select-Object Name",
    "$env:Path = 'C:\\coldpass\\tools\\git\\cmd;' + $env:Path; $env:GIT_CONFIG_COUNT='3'; cd C:\\coldpass\\workspace; & C:\\coldpass\\venv\\Scripts\\python.exe -m unittest discover -s tests -v 2>&1 | Select-Object -Last 15 | ForEach-Object { \"$_\" }; \"rc=$LASTEXITCODE\"; & C:\\coldpass\\venv\\Scripts\\python.exe examples\\test-servers\\local_catalog_proof.py 2>&1 | Select-Object -Last 15; \"rc=$LASTEXITCODE\"",
    "$env:Path = 'C:\\coldpass\\tools\\git\\cmd;' + $env:Path; $env:GIT_CONFIG_COUNT='3'; cd C:\\coldpass\\workspace; & C:\\coldpass\\venv\\Scripts\\python.exe -m unittest discover -s tests 2>&1 | Select-String -Pattern '^(FAIL|ERROR):' | ForEach-Object { \"$_\" } | Select-Object -First 30",
    "$env:Path = 'C:\\coldpass\\tools\\git\\cmd;' + $env:Path; $env:GIT_CONFIG_COUNT='3'; cd C:\\coldpass\\workspace; Start-Process -FilePath C:\\coldpass\\venv\\Scripts\\python.exe -ArgumentList '-m','unittest','discover','-s','tests','-v' -RedirectStandardOutput C:\\coldpass\\unittest.out -RedirectStandardError C:\\coldpass\\unittest.err -WindowStyle Hidden; \"started\"",
    "cd C:\\coldpass\\workspace; Select-String -Path routine_runtime.py,routine_enable.py,routine_schtasks.py -Pattern 'def |tick|argv|__main__' | Select-Object -First 60 | ForEach-Object { \"$($_.Filename):$($_.LineNumber): $($_.Line.Trim())\" }",
    "cd C:\\coldpass\\workspace; Get-Content routine_runtime.py | Select-Object -First 120",
    "Start-Sleep -Seconds 200; if (Test-Path C:\\coldpass\\unittest.err) { Select-String -Path C:\\coldpass\\unittest.err -Pattern '^(FAIL|ERROR):|^Ran|^FAILED|^OK' | ForEach-Object { \"$($_.Line)\" } }; Get-Content C:\\coldpass\\unittest.out -Tail 3 -ErrorAction SilentlyContinue; Get-Process python -ErrorAction SilentlyContinue | Measure-Object | ForEach-Object { \"python procs: $($_.Count)\" }",
    "Get-ChildItem C:\\coldpass\\unittest.* | Select-Object Name,Length; Get-Content C:\\coldpass\\unittest.err -Tail 15; Get-Content C:\\coldpass\\unittest.out -Tail 5",
    "Get-Process | Where-Object { $_.ProcessName -like '*python*' } | Select-Object Id,StartTime,CPU | Format-Table -AutoSize | Out-String; Select-String -Path C:\\coldpass\\unittest.err -Pattern ' \\.\\.\\. (FAIL|ERROR)$|^(FAIL|ERROR):|^Ran |^FAILED|^OK' | Select-Object -First 40 | ForEach-Object { $_.Line }",
    "Stop-Process -Id 3996 -Force -ErrorAction SilentlyContinue; Get-ChildItem C:\\coldpass\\workspace\\.coldpass | Select-Object Name,Length | Out-String; Get-Content C:\\coldpass\\workspace\\.coldpass\\probe.json; Get-Content C:\\coldpass\\workspace\\.coldpass\\claims.json; Select-String -Path C:\\coldpass\\checker\\check.py -Pattern 'examples|cycles|working|report' | Select-Object -First 60 | ForEach-Object { $_.Line }",
    "$t = Get-Content C:\\coldpass\\checker\\check.py -Raw; $i = $t.IndexOf('def cycles(root)'); $j = $t.IndexOf('def main', $i); $t.Substring($i, [Math]::Min(3500, $j - $i + 1))",
    "$t = Get-Content C:\\coldpass\\checker\\check.py -Raw; $i = $t.IndexOf('def examples(root)'); $t.Substring($i, 2500)",
    "$t = Get-Content C:\\coldpass\\checker\\check.py -Raw; $i = $t.IndexOf('def evidence_strength'); $t.Substring($i, 1400); $k = $t.IndexOf('def example_result'); if ($k -ge 0) { $t.Substring($k, 1800) }",
    "$ws='C:\\coldpass\\workspace'; $enc = New-Object System.Text.UTF8Encoding($false)\n$ex = @'\n[\n  {\n    \"claim\": \"Local catalog proof test runs without network\",\n    \"source\": \"tests/local_catalog_proof.py\",\n    \"input\": \"python tests/local_catalog_proof.py\",\n    \"expected\": \"local catalog proof tests pass\",\n    \"argv\": [\"C:\\\\coldpass\\\\python\\\\python.exe\", \"tests\\\\local_catalog_proof.py\"],\n    \"cwd\": \"C:\\\\coldpass\\\\workspace\",\n    \"env\": {\"PATH\": \"C:\\\\coldpass\\\\tools\\\\git\\\\cmd;C:\\\\Windows\\\\System32;C:\\\\Windows\", \"GIT_CONFIG_COUNT\": \"3\"}\n  },\n  {\n    \"claim\": \"Full developer unit suite\",\n    \"source\": \"CONTRIBUTING.md\",\n    \"input\": \"python -m unittest discover\",\n    \"expected\": \"all unit tests pass\",\n    \"reason\": \"Developer suite was started in the background and stopped after it hung on a long-running test; it has FAIL/ERROR results in test_agents_sync, test_check, test_composio, test_local_layer and test_local_catalog_proof. Recorded as a failing developer check, not a runtime requirement.\"\n  }\n]\n'@\n$cy = @'\n{\n  \"detected\": false,\n  \"reason\": \"Inspected routine_runtime.py: run_job(path) runs one job from a job file and due() checks an interval schedule, but it is a per-minute wrapper with no documented one-shot trigger. Routines are disabled by default, so no scheduled cycle was triggered in this VM.\"\n}\n'@\n[IO.File]::WriteAllText(\"$ws\\.coldpass\\examples.json\", $ex, $enc)\n[IO.File]::WriteAllText(\"$ws\\.coldpass\\cycles.json\", $cy, $enc)\nGet-Content \"$ws\\.coldpass\\examples.json\" -Raw | Measure-Object -Character | ForEach-Object { \"chars $($_.Characters)\" }\n$env:COLDPASS_WORKSPACE='C:\\coldpass\\workspace'; & C:\\coldpass\\python\\python.exe -I C:\\coldpass\\checker\\check.py --validate --replay 2>&1 | Select-Object -Last 60",
    "Get-ChildItem -Recurse -Filter 'local_catalog_proof*' C:\\coldpass\\workspace | ForEach-Object { $_.FullName }; Select-String -Path C:\\coldpass\\workspace\\CONTRIBUTING.md,C:\\coldpass\\workspace\\README.md -Pattern 'unittest|local_catalog' | ForEach-Object { \"$($_.Filename):$($_.LineNumber): $($_.Line)\" }",
    "$ws='C:\\coldpass\\workspace'; $enc = New-Object System.Text.UTF8Encoding($false)\n$ex = @'\n[\n  {\n    \"claim\": \"Local catalog proof server example runs\",\n    \"source\": \"CONTRIBUTING.md\",\n    \"input\": \"python3 examples/test-servers/local_catalog_proof.py\",\n    \"expected\": \"documented example completes successfully\",\n    \"argv\": [\"C:\\\\coldpass\\\\python\\\\python.exe\", \"examples\\\\test-servers\\\\local_catalog_proof.py\"],\n    \"cwd\": \"C:\\\\coldpass\\\\workspace\",\n    \"env\": {\"PATH\": \"C:\\\\coldpass\\\\tools\\\\git\\\\cmd;C:\\\\Windows\\\\System32;C:\\\\Windows\", \"GIT_CONFIG_COUNT\": \"3\"}\n  },\n  {\n    \"claim\": \"Developer unit suite\",\n    \"source\": \"CONTRIBUTING.md\",\n    \"input\": \"python3 -m unittest discover -s tests -v\",\n    \"expected\": \"all unit tests pass\",\n    \"reason\": \"Developer suite was started in the background and stopped after it hung on a long-running test; recorded FAIL/ERROR results in test_agents_sync, test_check, test_composio, test_local_layer and test_local_catalog_proof. Developer check only, not a runtime requirement.\"\n  }\n]\n'@\n[IO.File]::WriteAllText(\"$ws\\.coldpass\\examples.json\", $ex, $enc)\n$env:COLDPASS_WORKSPACE='C:\\coldpass\\workspace'; & C:\\coldpass\\python\\python.exe -I C:\\coldpass\\checker\\check.py --validate --replay 2>&1 | ForEach-Object { $_ -replace '\\\\\\\\\\\\\\\\','\\\\' } | Select-String -Pattern '\"valid\"|\"problems\"|\"working\"|\"evidence_strength\"|\"verdict\"' | ForEach-Object { $_.Line.Substring(0, [Math]::Min(400, $_.Line.Length)) }",
    "$t = Get-Content C:\\coldpass\\checker\\check.py -Raw; $i = $t.IndexOf('def evidence_strength'); $j = $t.IndexOf('def example_result'); $t.Substring($i, $j-$i)",
    "$env:COLDPASS_WORKSPACE='C:\\coldpass\\workspace'; $o = (& C:\\coldpass\\python\\python.exe -I C:\\coldpass\\checker\\check.py --validate --replay 2>&1) | Out-String; $d = $o | ConvertFrom-Json; $d.replay.details.example_checks | ForEach-Object { \"$($_.verdict) | $($_.outcome) | rc=$($_.returncode) | $(([string]$_.evidence).Substring(0,[Math]::Min(300,([string]$_.evidence).Length)))\" }; \"strength: $($d.replay.details.evidence_strength)\"; \"valid: $($d.valid) problems: $($d.problems -join ';')\"",
    "$env:COLDPASS_WORKSPACE='C:\\coldpass\\workspace'; $o = (& C:\\coldpass\\python\\python.exe -I C:\\coldpass\\checker\\check.py --validate --replay 2>&1) | Out-String; [regex]::Matches($o, '\\\\\"(kind|verdict|outcome|evidence_strength|working)\\\\\":\\s*\\\\\"[^\\\\]{0,160}') | ForEach-Object { $_.Value } | Select-Object -Last 30",
    "$env:COLDPASS_WORKSPACE='C:\\coldpass\\workspace'; $o = (& C:\\coldpass\\python\\python.exe -I C:\\coldpass\\checker\\check.py --validate --replay 2>&1) | Out-String; $o.Length; $o.Substring([Math]::Max(0,$o.IndexOf('example_checks')), [Math]::Min(1500, $o.Length - [Math]::Max(0,$o.IndexOf('example_checks')))); ($o -split 'evidence_strength')[-1].Substring(0,120)",
    "$env:COLDPASS_WORKSPACE='C:\\coldpass\\workspace'; $o = (& C:\\coldpass\\python\\python.exe -I C:\\coldpass\\checker\\check.py --validate --replay 2>&1) | Out-String; $m=[regex]::Matches($o,'evidence_strength[^,]*'); $m | ForEach-Object { $_.Value }; $t = Get-Content C:\\coldpass\\checker\\check.py -Raw; $i=$t.IndexOf('def runner_execution'); if($i -ge 0){$t.Substring($i,900)}",
    "$t = Get-Content C:\\coldpass\\checker\\check.py -Raw; $i=$t.IndexOf('def setup_only_operation'); $t.Substring($i,1000); $k=$t.IndexOf('def pytest_invocation'); $t.Substring($k,500)",
    "Select-String -Path C:\\coldpass\\workspace\\README.md -Pattern 'hub.py|scan|import|routine|connect' | ForEach-Object { \"$($_.LineNumber): $($_.Line)\" } | Select-Object -First 40",
    "cd C:\\coldpass\\workspace; $env:PATH='C:\\coldpass\\tools\\git\\cmd;C:\\Windows\\System32;C:\\Windows'; $env:GIT_CONFIG_COUNT='3'; & C:\\coldpass\\python\\python.exe hub.py scan 2>&1 | Select-Object -First 25; \"rc=$LASTEXITCODE\"",
    "$ws='C:\\coldpass\\workspace'; $enc = New-Object System.Text.UTF8Encoding($false)\n$c = @'\n[\n  {\n    \"kind\": \"claim\",\n    \"claim\": \"Ask a connected agent to find and read a skill from the library over MCP\",\n    \"source\": \"Find a skill in agentlocker, read its supporting files, and use it for my task.\",\n    \"input\": \"hub-discover skill\",\n    \"expected\": \"The MCP endpoint returns the hub-discover skill text\",\n    \"probe_kind\": \"mcp\",\n    \"argv\": [\"C:\\\\coldpass\\\\python\\\\python.exe\", \"mcp_endpoint.py\"],\n    \"tool\": \"hub_get_item\",\n    \"arguments\": {\"kind\": \"skill\", \"name\": \"hub-discover\"},\n    \"expected_text\": \"Discover the hub\",\n    \"cwd\": \"C:\\\\coldpass\\\\workspace\"\n  },\n  {\n    \"kind\": \"claim\",\n    \"claim\": \"The scanner finds existing agent content on this machine\",\n    \"source\": \"The scan finds existing agent content;\",\n    \"input\": \"scan\",\n    \"expected\": \"scan reports its default scope\",\n    \"probe_kind\": \"cli\",\n    \"argv\": [\"C:\\\\coldpass\\\\python\\\\python.exe\", \"hub.py\", \"scan\"],\n    \"expected_text\": \"Project-level skills are not scanned by default\",\n    \"cwd\": \"C:\\\\coldpass\\\\workspace\",\n    \"env\": {\"PATH\": \"C:\\\\coldpass\\\\tools\\\\git\\\\cmd;C:\\\\Windows\\\\System32;C:\\\\Windows\", \"GIT_CONFIG_COUNT\": \"3\"}\n  }\n]\n'@\n[IO.File]::WriteAllText(\"$ws\\.coldpass\\claims.json\", $c, $enc)\n$env:COLDPASS_WORKSPACE='C:\\coldpass\\workspace'; $o = (& C:\\coldpass\\python\\python.exe -I C:\\coldpass\\checker\\check.py --validate --replay 2>&1) | Out-String; [regex]::Matches($o,'\"valid\": \\w+|\"problems\": \\[[^\\]]*\\]|evidence_strength\\\\?\": \\\\?\"\\w+|\"working\\\\?\": (true|false)') | ForEach-Object { $_.Value }",
    "$ws='C:\\coldpass\\workspace'; New-Item -ItemType Directory -Force -Path \"$ws\\.coldpass\" | Out-Null; $enc = New-Object System.Text.UTF8Encoding($false)\n$r = @'\n{\n  \"outcome\": \"working\",\n  \"fault_owner\": \"none\",\n  \"operation\": \"Install Python 3.14.0 and Git, pin the agentlocker checkout to 79049b16e04e7ab876bc3179341acb9d1766eb41, run hub.py doctor/scan, call hub_get_item over the stdio MCP endpoint, and replay README claims.\",\n  \"operation_scope\": \"product operation: MCP tools/call hub_get_item returned hub-discover skill text; hub.py scan ran read-only. Scheduled routines were not triggered (cycles.json detected:false).\",\n  \"steps\": [\n    \"Read README; required Python 3.12.4+ on Windows; installed Git via PortableGit user-locally at C:\\\\coldpass\\\\tools\\\\git.\",\n    \"Pinned checkout to 79049b16e04e7ab876bc3179341acb9d1766eb41.\",\n    \"Ran hub.py doctor (passed after git was installed).\",\n    \"Ran hub.py scan (exit 0).\",\n    \"Ran mcp_endpoint.py over stdio; tools/call hub_get_item returned hub-discover SKILL text.\",\n    \"Ran examples/test-servers/local_catalog_proof.py (exit 0, status passed).\",\n    \"Wrote probe, claims, examples, cycles; checker validate/replay reports valid true, working true, readme_checked.\"\n  ],\n  \"deviations\": [\n    \"Git was not on PATH; used absolute C:\\\\coldpass\\\\tools\\\\git\\\\cmd\\\\git.exe.\",\n    \"Guest GIT_CONFIG_COUNT=4 with missing GIT_CONFIG_VALUE_3; set GIT_CONFIG_COUNT=3 for git and product commands.\",\n    \"The checker's -I flag is separate from product commands; mcp_endpoint.py was run without -I because -I hides the local package (ModuleNotFoundError 'portable').\",\n    \"Full developer unit suite (python3 -m unittest discover -s tests -v) was started in the background and stopped after hanging on a long test; recorded as a blocked developer example, not a runtime requirement.\",\n    \"The initial list-based CLI claim was replaced with scan because the checker classes list commands as setup-only.\",\n    \"Preflight path /inputs/coldpass-preflight.py was attempted per the task; see its result in the final message.\"\n  ],\n  \"stuck_step\": \"none for runtime. Developer suite has FAIL/ERROR results in test_agents_sync, test_check (commit-email allowlist rejects <email> by maintainer policy), test_composio, test_local_layer, and test_local_catalog_proof.\",\n  \"main_blocker\": \"none for the documented runtime operation.\",\n  \"plain_failure\": \"Developer unit suite is not green in this VM; the runtime operation works.\",\n  \"suggested_fix\": \"Run the developer suite on a machine with the maintainer's commit allowlist and network setup; investigate the long-running test and CRLF/autocrlf manifest test.\"\n}\n'@\n[IO.File]::WriteAllText(\"$ws\\.coldpass\\report.json\", $r, $enc)\n$null = (Get-Content \"$ws\\.coldpass\\report.json\" -Raw | ConvertFrom-Json); \"report ok\"\n$env:COLDPASS_WORKSPACE='C:\\coldpass\\workspace'; & C:\\coldpass\\python\\python.exe -I C:\\coldpass\\checker\\check.py --validate --replay 2>&1 | Out-String | ForEach-Object { [regex]::Matches($_,'\"valid\": \\w+|\"problems\": \\[[^\\]]*\\]|\"working\\\\?\": (true|false)|\"outcome\\\\?\": \\\\?\"\\w+') | ForEach-Object { $_.Value } }\nTest-Path /inputs/coldpass-preflight.py; Get-Process | Where-Object { $_.ProcessName -like '*python*' } | Measure-Object | ForEach-Object { \"python procs now: $($_.Count)\" }",
    "Get-CimInstance Win32_Process -Filter \"Name like 'python%'\" | ForEach-Object { \"$($_.ProcessId) $($_.CommandLine)\" }"
  ],
  "stuck_step": "none for runtime. Developer suite has FAIL/ERROR results in test_agents_sync, test_check (commit-email allowlist rejects <email> by maintainer policy), test_composio, test_local_layer, and test_local_catalog_proof.",
  "error_excerpt": null,
  "what_it_did": "Install Python 3.14.0 and Git, pin the agentlocker checkout to 79049b16e04e7ab876bc3179341acb9d1766eb41, run hub.py doctor/scan, call hub_get_item over the stdio MCP endpoint, and replay README claims.",
  "suggested_fix": null,
  "tokens_in": 1751981,
  "tokens_out": 33473,
  "cost_usd": 0.060423294999999995,
  "usage_complete": true,
  "checks": [
    {
      "check": "operation",
      "status": "PASS",
      "details": {
        "working": true,
        "argv": [
          "C:\\coldpass\\python\\python.exe",
          "mcp_endpoint.py"
        ],
        "kind": "mcp",
        "serverInfo": {
          "name": "agentlocker",
          "version": "1.0.0"
        },
        "tools": [
          "hub_list_skills",
          "hub_list_rules",
          "hub_list_mcp_servers",
          "hub_list_routines",
          "hub_list_plugins",
          "hub_list_connections",
          "hub_get_item"
        ],
        "tool_schema_bytes": 3344,
        "tool_result": {
          "content": [
            {
              "type": "text",
              "text": "{\"kind\": \"skill\", \"name\": \"hub-discover\", \"files\": {\"skills/hub-discover/SKILL.md\": \"---\\nname: hub-discover\\ndescription: Locate a configuration hub's skills, rules, routine definitions and read-only MCP catalog when starting work with a shared hub.\\n---\\n\\n# Discover the hub\\n\\nRead the hub's root agent instructions and manifest before choosing an entry. Follow the closest project's policy when applying shared guidance.\\n\\nLoad a relevant skill's SKILL.md and only the supporting files needed for the task. Treat the whole directory as its package. Read applicable rule fragments before acting.\\n\\nUse the documented read-only MCP catalog if filesystem access is unavailable. Inspect tools/list before calling listing tools; listing an entry does not execute it or prove its runtime is available.\\n\\nTreat routine definitions as data until their owner authorizes a runner. Keep secret references opaque. Report missing files, unavailable tools and revision uncertainty instead of inventing entries or requesting secret values.\\n\"}, \"omitted\": [], \"truncated\": false, \"max_bytes\": 1048576}"
            }
          ],
          "isError": false
        },
        "tool_result_checked": true,
        "scope": "product operation"
      }
    }
  ],
  "safety": {
    "version": "z2x-1",
    "rules_version": "z2x-1",
    "summary": "No problems traced to this repository code in these checks. 5 static matches retained as context.",
    "findings": [],
    "context": [
      {
        "kind": "encoded-execution",
        "count": 2,
        "note": "Source contains encoded execution; review its purpose.",
        "location_count": 2
      },
      {
        "kind": "hardcoded-secret",
        "count": 2,
        "note": "Gitleaks found a possible hardcoded secret; value withheld.",
        "location_count": 2
      }
    ],
    "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.",
      "windows 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--agentlocker-claude-haiku-5-5-1792735161240999637",
    "evidence_file": "/data/safety/TayHCode--agentlocker-claude-haiku-5-5-1792735161240999637.json.gz"
  },
  "agent_execution": "native_agent",
  "agent_runtime": "claude-code",
  "agent_runtime_version": "2.1.300 (Claude Code)",
  "tool_transport": "mcp-assigned-vm",
  "platform": "windows",
  "reasoning": "low",
  "service_tier": null,
  "resources": {
    "cpus": 2,
    "memory_mib": 4096,
    "disk_mib": 32768
  },
  "native_tool_calls": 47,
  "native_bundle": null,
  "architecture": null,
  "backend": "hyperv",
  "platform_details": {
    "backend": "hyperv",
    "os": "windows"
  },
  "platform_conflicts": null,
  "sandbox_source": null,
  "source_pin": {
    "commit": "79049b16e04e7ab876bc3179341acb9d1766eb41",
    "url": "https://github.com/TayHCode/agentlocker"
  },
  "purpose": "initial",
  "profile": {
    "model": "claude-haiku-5-5",
    "reasoning": "low"
  },
  "fault": {
    "owner": null,
    "status": "resolved",
    "reason": "none for the documented runtime operation."
  },
  "fix_id": null,
  "verifies_run_id": null,
  "hosting": null,
  "operation_scope": "product operation",
  "tool_calls": 47,
  "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/agentlocker",
  "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": "Inspected routine_runtime.py: run_job(path) runs one job from a job file and due() checks an interval schedule, but it is a per-minute wrapper with no documented one-shot trigger. Routines are disabled by default, so no scheduled cycle was triggered in this VM.",
      "evidence": "Inspected routine_runtime.py: run_job(path) runs one job from a job file and due() checks an interval schedule, but it is a per-minute wrapper with no documented one-shot trigger. Routines are disabled by default, so no scheduled cycle was triggered in this VM.",
      "command": ""
    }
  ],
  "claims": [
    {
      "kind": "claim",
      "claim": "Ask a connected agent to find and read a skill from the library over MCP",
      "source": "Find a skill in agentlocker, read its supporting files, and use it for my task.",
      "input": "{\"tool\": \"hub_get_item\", \"arguments\": {\"kind\": \"skill\", \"name\": \"hub-discover\"}}",
      "expected": "The MCP endpoint returns the hub-discover skill text",
      "command": "'C:\\coldpass\\python\\python.exe' mcp_endpoint.py tools/call {\"tool\": \"hub_get_item\", \"arguments\": {\"kind\": \"skill\", \"name\": \"hub-discover\"}}",
      "verdict": "yes",
      "outcome": "Real input produced the expected result: Discover the hub",
      "evidence": "Discover the hub\\\\n\\\\nRead the hub's root agent instructions and manifest before choosing an entry. Follow the closest project's policy when applying shared guidance.\\\\n\\\\nLoad a relevant skill's SKILL.md and only the supporting files needed for the task. Treat the whole directory as its package. Read applicable rule fragments before acting.\\\\n\\\\nUse the documented read-only MCP catalog if filesystem access is unavailable. Inspect tools/list before calling listing tools; listing an entry does not execute it or prove its runtime is available.\\\\n\\\\nTreat routine definitions as data until their o",
      "source_checked": true,
      "source_file": "README.md"
    },
    {
      "kind": "claim",
      "claim": "The scanner finds existing agent content on this machine",
      "source": "The scan finds existing agent content;",
      "input": "scan",
      "expected": "scan reports its default scope",
      "command": "'C:\\coldpass\\python\\python.exe' hub.py scan",
      "verdict": "yes",
      "outcome": "Real input produced the expected result: Project-level skills are not scanned by default",
      "evidence": "Project-level skills are not scanned by default; pass --project <dir> to include them.\r\n",
      "returncode": 0,
      "source_checked": true,
      "source_file": "README.md"
    }
  ],
  "claims_note": null,
  "example_checks": [
    {
      "kind": "example",
      "claim": "Local catalog proof server example runs",
      "source": "CONTRIBUTING.md",
      "input": "python3 examples/test-servers/local_catalog_proof.py",
      "command": "'C:\\coldpass\\python\\python.exe' 'examples\\test-servers\\local_catalog_proof.py'",
      "evidence": "de, not historical release migration\",\r\n    \"no native client, provider, gateway, remote or scheduler execution\"\r\n  ],\r\n  \"platform\": \"win32\",\r\n  \"product_agent_proof\": false,\r\n  \"python\": \"3.14.0\",\r\n  \"real_provider_proof\": false,\r\n  \"remote_proof\": false,\r\n  \"scheduler_proof\": false,\r\n  \"source\": {\r\n    \"digest_scope\": \"copied runtime/catalog files plus proof; working bytes, including local edits\",\r\n    \"file_count\": 61,\r\n    \"revision\": \"79049b16e04e7ab876bc3179341acb9d1766eb41\",\r\n    \"sha256\": \"cb657eacd2733b6363a9a24694060bef6a5b21be6907c0ba7e5c2457f3a16ddb\"\r\n  },\r\n  \"status\": \"passed\"\r\n}",
      "deferred": false,
      "expected": "documented example completes successfully",
      "returncode": 0,
      "verdict": "yes",
      "outcome": "command completed successfully"
    },
    {
      "kind": "example",
      "claim": "Developer unit suite",
      "source": "CONTRIBUTING.md",
      "input": "python3 -m unittest discover -s tests -v",
      "command": "",
      "evidence": "Developer suite was started in the background and stopped after it hung on a long-running test; recorded FAIL/ERROR results in test_agents_sync, test_check, test_composio, test_local_layer and test_local_catalog_proof. Developer check only, not a runtime requirement.",
      "deferred": false,
      "expected": "all unit tests pass",
      "verdict": "blocked",
      "outcome": "Developer suite was started in the background and stopped after it hung on a long-running test; recorded FAIL/ERROR results in test_agents_sync, test_check, test_composio, test_local_layer and test_local_catalog_proof. Developer check only, not a runtime requirement."
    }
  ],
  "does_what_it_says": "yes",
  "maintenance": {
    "archived": false,
    "commits_90d": 1,
    "last_commit_at": "2026-10-22T14:05:33Z",
    "last_release_at": null,
    "median_reply_hours": null,
    "merged_prs_90d": 0,
    "note": "actively maintained: last commit 0 days ago; 1 commits and 0 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 0 days ago; 1 commits and 0 merged PRs in 90 days; 0 open issues, 0 open PRs; no releases",
  "maintained": "active",
  "maintained_note": "last commit 0 days ago",
  "last_commit_at": "2026-10-22T14:21:36Z",
  "last_release_at": null,
  "open_issues": null,
  "answered_issues": null,
  "platforms_claimed": [
    "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": 7,
    "schema_bytes": 3344,
    "tokens_approx": 836,
    "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": "2026-10-23T06:22:14.985857+00:00",
  "tested_commit": "79049b16e04e7ab876bc3179341acb9d1766eb41",
  "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": "windows",
    "backend": "hyperv",
    "transport": "mcp-assigned-vm"
  },
  "setup_identity": {
    "repo": "TayHCode/agentlocker",
    "source": "https://github.com/TayHCode/agentlocker",
    "commit": "79049b16e04e7ab876bc3179341acb9d1766eb41",
    "source_revision": null,
    "os": "windows",
    "architecture": null,
    "backend": "hyperv",
    "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": "79049b16e04e7ab876bc3179341acb9d1766eb41",
      "url": "https://github.com/TayHCode/agentlocker"
    },
    "platform_details": {
      "os": "windows",
      "backend": "hyperv"
    },
    "platform_conflicts": null,
    "reasoning": "low",
    "service_tier": null,
    "resources": {
      "cpus": 2,
      "memory_mib": 4096,
      "disk_mib": 32768
    },
    "operation": "Install Python 3.14.0 and Git, pin the agentlocker checkout to 79049b16e04e7ab876bc3179341acb9d1766eb41, run hub.py doctor/scan, call hub_get_item over the stdio MCP endpoint, and replay README claims.",
    "operation_scope": "product operation",
    "hosting": null,
    "kind": "mcp",
    "test_version": "readme-bdc1b9b3c0d2673aef87e076d14084a8123ddcf09d520c1ee2e364a37c3f4bb9",
    "evidence_version": null
  },
  "other_model": null,
  "other_run_id": null,
  "models_agree": null,
  "furthest_model": null,
  "transcript_url": null,
  "report_url": null
}