{ "run_id": "VoltAgent--awesome-codex-subagents-gpt-6-luna-1792761050049468099", "date": "2026-10-23T13:11:58.853714+00:00", "repo": "VoltAgent/awesome-codex-subagents", "kind": "repo", "source": "https://github.com/VoltAgent/awesome-codex-subagents", "commit": "16f880a2a0486f880da75d2baffcd68af4cc4811", "model": "gpt-6-luna", "model_version": "gpt-6-luna", "test_version": "readme-f72312298d35d84837d4fc5f6f22b138d54d456600b5ed431e36e8f5db931dbf", "pass": true, "outcome": "pass", "time_to_working_s": 44.87323505803943, "total_s": 68.80418038368225, "steps": [ "pwd; id -u; rg --files -g 'README*' -g 'AGENTS.md' -g 'pyproject.toml' -g 'package.json' -g 'Makefile' -g '.github/workflows/**' | head -80; git status --short --branch; git rev-parse --show-toplevel 2>&1; python3 --version; cat README.md", "git init; git remote add origin https://github.com/VoltAgent/awesome-codex-subagents; git fetch --depth 1 origin 16f880a2a0486f880da75d2baffcd68af4cc4811; git reset --mixed FETCH_HEAD; find . -name AGENTS.md -o -name '*test*' | head -60; find .github -type f 2>/dev/null; sed -n '1,100p' categories/01-core-development/backend-developer.toml; ls -la", "mkdir -p ; mkdir -p ; cp categories/01-core-development/backend-developer.toml ; cat ", "cat > .coldpass/probe.json <<'EOF'\n{\"kind\":\"cli\",\"argv\":[\"cp\",\"categories/01-core-development/backend-developer.toml\",\"\"],\"cwd\":\"\",\"expected_text\":\"backend-developer\"}\nEOF\ncat > .coldpass/claims.json <<'EOF'\n[{\"kind\":\"claim\",\"claim\":\"Installation copies selected TOML agent files into a Codex agents directory.\",\"source\":\"Copy the `.toml` agent files you want into one of the directories above.\",\"input\":\"categories/01-core-development/backend-developer.toml\",\"expected\":\"backend-developer.toml is copied and contains name = \\\"backend-developer\\\"\",\"probe_kind\":\"cli\",\"argv\":[\"cp\",\"categories/01-core-development/backend-developer.toml\",\"\"],\"expected_text\":\"backend-developer\"}]\nEOF\ncat > .coldpass/examples.json <<'EOF'\n[{\"kind\":\"example\",\"claim\":\"README global agent installation example\",\"source\":\"README.md / Installation\",\"input\":\"backend-developer.toml\",\"expected\":\"file copied to agents directory\",\"argv\":[\"bash\",\"-c\",\"mkdir -p && cp categories/01-core-development/backend-developer.toml && cat \"],\"cwd\":\"\",\"expected_text\":\"name = \\\"backend-developer\\\"\"}]\nEOF\ncat > .coldpass/cycles.json <<'EOF'\n{\"detected\":false,\"reason\":\"README and repository entry points contain agent definitions and installation instructions, with no product scheduler or recurring cycle.\",\"checks\":[]}\nEOF\n= python3 -I --validate --replay", "cat .coldpass/probe.json; cat .coldpass/claims.json", "python3 - <<'PY'\nimport json\np='.coldpass/probe.json'; d=json.load(open(p)); d.update(argv=['bash','-c','cp categories/01-core-development/backend-developer.toml && cat ']); json.dump(d,open(p,'w'))\np='.coldpass/claims.json'; d=json.load(open(p)); d[0]['argv']=['bash','-c','cp categories/01-core-development/backend-developer.toml && cat ']); json.dump(d,open(p,'w'))\nPY\n= python3 -I --validate --replay", "python3 - <<'PY'\nimport json\np='.coldpass/probe.json'\nd=json.load(open(p)); d['argv']=['bash','-c','cp categories/01-core-development/backend-developer.toml && cat ']; json.dump(d,open(p,'w'))\np='.coldpass/claims.json'\nd=json.load(open(p)); d[0]['argv']=['bash','-c','cp categories/01-core-development/backend-developer.toml && cat ']; json.dump(d,open(p,'w'))\nPY\n= python3 -I --validate --replay", "cat > .coldpass/report.json <<'EOF'\n{\"outcome\":\"working\",\"fault_owner\":null,\"operation\":\"Copy and read a selected Codex agent definition\",\"operation_scope\":\"README installation example, using the backend-developer TOML in a temporary agents directory\",\"steps\":[\"Read README installation instructions.\",\"Fetched pinned commit 16f880a2a0486f880da75d2baffcd68af4cc4811.\",\"Copied the documented agent file and read it back; confirmed name = backend-developer.\",\"Validated and replayed probe, README claim, example, and cycle record successfully.\"],\"deviations\":[\"Repository is a static agent-definition collection with no build, runtime, tests, or product scheduler; used its documented copy-and-use operation.\"],\"stuck_step\":null,\"main_blocker\":null,\"plain_failure\":null,\"suggested_fix\":null}\nEOF\n" ], "stuck_step": null, "error_excerpt": null, "what_it_did": "Copy and read a selected Codex agent definition", "suggested_fix": null, "tokens_in": 170716, "tokens_out": 1682, "cost_usd": null, "usage_complete": true, "checks": [ { "check": "operation", "status": "PASS", "details": { "working": true, "argv": [ "bash", "-c", "cp categories/01-core-development/backend-developer.toml && cat " ], "kind": "cli", "returncode": 0, "stdout": "name = \"backend-developer\"\ndescription = \"Use when a task needs scoped backend implementation or backend bug fixes after the owning path is known.\"\nmodel = \"gpt-5.6-sol\"\nmodel_reasoning_effort = \"high\"\nsandbox_mode = \"workspace-write\"\ndeveloper_instructions = \"\"\"\nOwn backend changes as production behavior with explicit data, auth, and failure-path integrity.\n\nWorking mode:\n1. Map entry point, domain logic boundary, and persistence side effects.\n2. Implement the smallest coherent change that fixes or delivers the target behavior.\n3. Validate behavior under normal and high-risk failure paths.\n[excerpt truncated]", "stderr": "", "needs_credentials": false, "needs_browser": false, "scope": "product operation" } } ], "safety": { "version": "z2x-1", "rules_version": "z2x-1", "summary": "No problems traced to this repository code in these checks.", "findings": [], "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." ], "static": { "dependency_note": "OSV scanned supported lockfiles; unpinned dependencies and unsupported formats are outside this check." }, "evidence_url": "/safety/?run=VoltAgent--awesome-codex-subagents-gpt-6-luna-1792761050049468099", "evidence_file": "/data/safety/VoltAgent--awesome-codex-subagents-gpt-6-luna-1792761050049468099.json.gz" }, "agent_execution": "native_agent", "agent_runtime": "codex", "agent_runtime_version": "codex-cli 0.163.0", "tool_transport": "mcp-assigned-vm", "platform": "linux", "reasoning": "low", "service_tier": "standard", "resources": { "cpus": 2, "memory_mib": 4096, "disk_mib": 32768 }, "native_tool_calls": 8, "native_bundle": null, "architecture": null, "backend": "hyperv", "platform_details": { "backend": "hyperv", "os": "linux" }, "platform_conflicts": null, "sandbox_source": null, "source_pin": { "commit": "16f880a2a0486f880da75d2baffcd68af4cc4811", "url": "https://github.com/VoltAgent/awesome-codex-subagents" }, "purpose": "initial", "profile": { "model": "gpt-6-luna", "reasoning": "low" }, "fault": { "owner": null, "status": "resolved", "reason": null }, "fix_id": null, "verifies_run_id": null, "hosting": null, "operation_scope": "product operation", "tool_calls": 8, "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": "none", "needs": [], "needs_which": null, "agent_interface": [ "cli" ], "license": "MIT", "repo_url": "https://github.com/VoltAgent/awesome-codex-subagents", "cost_to_try": "free", "hardware": null, "what_failed": null, "local_or_hosted": "hosted", "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": "README and repository entry points contain agent definitions and installation instructions, with no product scheduler or recurring cycle.", "evidence": "README and repository entry points contain agent definitions and installation instructions, with no product scheduler or recurring cycle.", "command": "" } ], "claims": [ { "kind": "claim", "claim": "Installation copies selected TOML agent files into a Codex agents directory.", "source": "Copy the `.toml` agent files you want into one of the directories above.", "input": "categories/01-core-development/backend-developer.toml", "expected": "backend-developer.toml is copied and contains name = \"backend-developer\"", "command": "bash -c 'cp categories/01-core-development/backend-developer.toml && cat '", "verdict": "yes", "outcome": "Real input produced the expected result: backend-developer", "evidence": "backend-developer\"\ndescription = \"Use when a task needs scoped backend implementation or backend bug fixes after the owning path is known.\"\nmodel = \"gpt-5.6-sol\"\nmodel_reasoning_effort = \"high\"\nsandbox_mode = \"workspace-write\"\ndeveloper_instructions = \"\"\"\nOwn backend changes as production behavior with explicit data, auth, and failure-path integrity.\n\nWorking mode:\n1. Map entry point, domain logic boundary, and persistence side effects.\n2. Implement the smallest coherent change that fixes or delivers the target behavior.\n3. Validate behavior under normal and high-risk failure paths.\n\nFocus on:", "returncode": 0, "source_checked": true, "source_file": "README.md" } ], "claims_note": null, "example_checks": [ { "kind": "example", "claim": "README global agent installation example", "source": "README.md / Installation", "input": "backend-developer.toml", "command": "bash -c 'mkdir -p && cp categories/01-core-development/backend-developer.toml && cat '", "evidence": "pe\n- make failure semantics explicit (timeouts, not found, conflict, transient failure)\n\nQuality checks:\n- validate one critical success path and one high-risk failure path\n- verify persistence and rollback behavior for changed write paths\n- ensure changed path still enforces auth/permission rules\n- call out environment dependencies not verifiable in local checks\n\nReturn:\n- files and backend path changed\n- behavior change summary\n- validation performed\n- residual risk and follow-up verification needed\n\nDo not broaden into unrelated refactors unless explicitly requested by the parent agent.\n\"\"\"", "deferred": false, "expected": "file copied to agents directory", "returncode": 0, "verdict": "yes", "outcome": "command completed successfully" } ], "does_what_it_says": "yes", "maintenance": { "last_commit_at": "2026-10-05T07:40:02Z", "commits_90d": 17, "merged_prs_90d": 2, "open_issues": 0, "open_prs": 0, "reply_share": 0.13, "reply_threads": 31, "median_reply_hours": 52.7, "last_release_at": null, "archived": false, "verdict": "maintained", "note": "actively maintained: last commit 18 days ago; 17 commits and 2 merged PRs in 90 days; 0 open issues, 0 open PRs; 4 of 31 recent threads got a maintainer reply, median first reply 52.7h; no releases" }, "maintenance_verdict": "maintained", "maintenance_note": "actively maintained: last commit 18 days ago; 17 commits and 2 merged PRs in 90 days; 0 open issues, 0 open PRs; 4 of 31 recent threads got a maintainer reply, median first reply 52.7h; no releases", "maintained": "active", "maintained_note": "last commit 18 days ago; 0 open issues, 5 answered or closed", "last_commit_at": "2026-10-05T07:40:02Z", "last_release_at": null, "open_issues": 0, "answered_issues": 5, "platforms_claimed": [ "mac", "windows" ], "topic": "agent-harness", "agent_interfaces": [ { "interface": "mcp", "evidence": "README metadata", "observed": false, "operation_checked": false }, { "interface": "cli", "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": null, "tested_at": "2026-10-23T13:11:58.853714+00:00", "tested_commit": "16f880a2a0486f880da75d2baffcd68af4cc4811", "tested_with": { "agent": "codex", "agent_version": "codex-cli 0.163.0", "model": "gpt-6-luna", "model_route": "gpt-6-luna", "reasoning": "low", "os": "linux", "backend": "hyperv", "transport": "mcp-assigned-vm" }, "setup_identity": { "repo": "VoltAgent/awesome-codex-subagents", "source": "https://github.com/VoltAgent/awesome-codex-subagents", "commit": "16f880a2a0486f880da75d2baffcd68af4cc4811", "source_revision": null, "os": "linux", "architecture": null, "backend": "hyperv", "model": "gpt-6-luna", "model_version": "gpt-6-luna", "agent_execution": "native_agent", "agent_runtime": "codex", "agent_runtime_version": "codex-cli 0.163.0", "tool_transport": "mcp-assigned-vm", "runtime": null, "runtime_version": null, "runtime_revision": null, "sandbox_source": null, "guest_setup": null, "source_pin": { "commit": "16f880a2a0486f880da75d2baffcd68af4cc4811", "url": "https://github.com/VoltAgent/awesome-codex-subagents" }, "platform_details": { "os": "linux", "backend": "hyperv" }, "platform_conflicts": null, "reasoning": "low", "service_tier": "standard", "resources": { "cpus": 2, "memory_mib": 4096, "disk_mib": 32768 }, "operation": "Copy and read a selected Codex agent definition", "operation_scope": "product operation", "hosting": null, "kind": "repo", "test_version": "readme-f72312298d35d84837d4fc5f6f22b138d54d456600b5ed431e36e8f5db931dbf", "evidence_version": null }, "other_model": null, "other_run_id": null, "models_agree": null, "furthest_model": null, "transcript_url": null, "report_url": "/reports/VoltAgent--awesome-codex-subagents-gpt-6-luna-1792761050049468099.json" }