{ "run_id": "mattpocock--skills-gpt-6-luna-1792785874620899102", "date": "2026-10-23T20:21:47.602841+00:00", "repo": "mattpocock/skills", "kind": "repo", "source": "https://github.com/mattpocock/skills", "commit": "5beb35b040e3de97e54fa9e386d7e42d15c295c2", "model": "gpt-6-luna", "model_version": "gpt-6-luna", "test_version": "readme-f72312298d35d84837d4fc5f6f22b138d54d456600b5ed431e36e8f5db931dbf", "pass": true, "outcome": "pass", "time_to_working_s": 983.8230488260742, "total_s": 1032.9819180965424, "steps": [ "pwd; rg --files -g 'README*' -g 'AGENTS.md' -g 'package.json' -g 'pyproject.toml' -g 'Makefile' -g '.github/workflows/**' | head -80; id -u; python3 --version; vault-search 'mattpocock skills repo setup install README MCP operation' 2>&1 | head -80; ls -la ~/.agents/skills/i-have-adhd/SKILL.md ~/.agents/skills/ponytail/SKILL.md ~/.agents/skills/p3-mode/SKILL.md 2>&1", "find . -maxdepth 3 -type f | sort | head -100; sed -n '1,240p' README.md; git status --short --branch 2>&1; git log -1 --oneline 2>&1", "cat package.json; find skills -mindepth 3 -maxdepth 3 -name SKILL.md | head -20; find . -name AGENTS.md -o -name 'CLAUDE.md' | head; ls -ld node_modules 2>/dev/null || true; git --version; node --version 2>&1; npm --version 2>&1", "cat AGENTS.md; git init; git remote add origin https://github.com/mattpocock/skills; git fetch --depth 1 origin 5beb35b040e3de97e54fa9e386d7e42d15c295c2; git reset --mixed FETCH_HEAD", "cat .agents/install-block.md; sed -n '1,240p' skills/engineering/setup-matt-pocock-skills/SKILL.md; cat .claude-plugin/plugin.json; python3 - <<'PY'\nfrom pathlib import Path\np=Path('README.md').read_text()\nfor line in p.splitlines():\n if 'skills@latest add' in line or 'Run `/setup-matt' in line or '3. Bam' in line: print(repr(line))\nPY\nsudo -n apt-get update && sudo -n apt-get install -y nodejs npm", "node --version; npm --version; NODE_USE_ENV_PROXY=1 npx --yes skills@latest add mattpocock/skills --skill=teach --agent=codex --yes", "curl -fsSL https://deb.nodesource.com/setup_22.x | sudo -n -E bash -; sudo -n apt-get install -y nodejs; node --version; npm --version", "mkdir -p .coldpass; cd /tmp && NODE_USE_ENV_PROXY=1 npx --yes skills@latest add mattpocock/skills --skill=teach --agent=codex --yes", "find . -maxdepth 3 -type f -path '*/.agents/skills/*/SKILL.md' | head; python3 - <<'PY'\nimport json, pathlib\np=pathlib.Path('.coldpass'); p.mkdir(exist_ok=True)\nprobe={\"kind\":\"cli\",\"argv\":[\"npx\",\"--yes\",\"skills@latest\",\"add\",\"mattpocock/skills\",\"--skill=teach\",\"--agent=codex\",\"--yes\"],\"cwd\":\"/tmp\",\"env\":{\"NODE_USE_ENV_PROXY\":\"1\"},\"expected_text\":\"Installation complete\"}\nclaims=[{\"kind\":\"claim\",\"claim\":\"The skills.sh install copies editable skills for the selected agent.\",\"source\":\"`skills.sh` (https://skills.sh/mattpocock/skills) copies editable files into your project, and you update them by hand.\",\"input\":\"teach skill for Codex\",\"expected\":\"Installation complete\",\"probe_kind\":\"cli\",\"argv\":probe['argv'],\"cwd\":\"/tmp\",\"env\":{\"NODE_USE_ENV_PROXY\":\"1\"},\"expected_text\":\"Installation complete\"}]\nexamples=[{\"kind\":\"example\",\"claim\":\"Install the teach skill for Codex via the documented skills.sh command.\",\"source\":\"README.md, Installation (30-second setup), Any other agent, or editable files\",\"input\":\"teach skill for Codex\",\"expected\":\"Installation completes\",\"argv\":probe['argv'],\"cwd\":\"/tmp\",\"env\":{\"NODE_USE_ENV_PROXY\":\"1\"},\"expected_text\":\"Installation complete\"}]\n(p/'probe.json').write_text(json.dumps(probe,indent=2)+'\\n')\n(p/'claims.json').write_text(json.dumps(claims,indent=2)+'\\n')\n(p/'examples.json').write_text(json.dumps(examples,indent=2)+'\\n')\n(p/'cycles.json').write_text(json.dumps({\"detected\":False,\"reason\":\"Inspected README and package.json entry points; this repository distributes prompt-invoked skills and has no product scheduler or recurring cycle entry point.\",\"checks\":[]},indent=2)+'\\n')\nPY\n= python3 -I --validate --replay", "python3 - <<'PY'\nimport json,pathlib\np=pathlib.Path('.coldpass/claims.json'); c=json.loads(p.read_text()); c[0]['source']='`skills.sh` (https://skills.sh/mattpocock/skills) copies editable files into your project, and you update them by hand. Pick one per agent, because installing both gives you every skill twice.'; p.write_text(json.dumps(c,indent=2)+'\\n')\nPY\n= python3 -I --validate --replay", "python3 - <<'PY'\nimport json\nc=json.load(open('.coldpass/claims.json')); print(repr(c[0]['source'])); print(repr(open('README.md').read().splitlines()[11]))\nPY\nnl -ba README.md | head -40", "python3 - <<'PY'\nimport json,pathlib\np=pathlib.Path('.coldpass/claims.json'); c=json.loads(p.read_text()); c[0]['source']='A plugin updates itself. [skills.sh](https://skills.sh/mattpocock/skills) copies editable files into your project, and you update them by hand. Pick one per agent, because installing both gives you every skill twice.'; p.write_text(json.dumps(c,indent=2)+'\\n')\nPY\n= python3 -I --validate --replay", "python3 - <<'PY'\nimport json,pathlib\np=pathlib.Path('.coldpass/report.json')\nr={\"outcome\":\"working\",\"fault_owner\":None,\"operation\":\"Install a documented skills.sh skill into the project\",\"operation_scope\":\"Selected the teach skill for Codex with Node.js 22 and npx; installer completed successfully.\",\"steps\":[\"Read README.md and checked out pinned commit 5beb35b040e3de97e54fa9e386d7e42d15c295c2.\",\"Installed Node.js 22 after the installer revealed that skills@latest requires Node >=22.20.0.\",\"Ran the README skills.sh add command for the teach skill and Codex; installation completed.\",\"Validated and replayed probe, README claim, example, and cycle assessment successfully.\"],\"deviations\":[\"Initial distro Node.js 18 failed the installer requirement; upgraded to Node.js 22.\",\"The README setup skill requires interactive user choices, so its configuration flow was inspected but not invoked.\"],\"stuck_step\":None,\"main_blocker\":None,\"plain_failure\":None,\"suggested_fix\":None}\np.write_text(json.dumps(r,indent=2)+'\\n')\nPY\ncat .coldpass/report.json; git rev-parse HEAD" ], "stuck_step": null, "error_excerpt": null, "what_it_did": "Install a documented skills.sh skill into the project", "suggested_fix": null, "tokens_in": 692436, "tokens_out": 3121, "cost_usd": null, "usage_complete": true, "checks": [ { "check": "operation", "status": "PASS", "details": { "working": true, "argv": [ "npx", "--yes", "skills@latest", "add", "mattpocock/skills", "--skill=teach", "--agent=codex", "--yes" ], "kind": "cli", "returncode": 0, "stdout": "al: Amp, Antigravity, Antigravity CLI, Cline, Codex +19 more \u2502\n\u2502 symlinked: Claude Code, Eve \u2502\n\u2502 skipped: AiderDesk, AstrBot, Autohand Code CLI, Augment, IBM Bob +48 \u2502\n\u2502 more (project directory not found) \u2502\n\u2502 \u2713 ./.agents/skills/pr \u2502\n\u2502 universal: Amp, Antigravity, Antigravity CLI, Cline, Codex +19 more \u2502\n\u2502 symlinked: Claude Code, Eve \u2502\n\u2502 skipped: AiderDesk, AstrBot, Autohand Code CLI, Augment, IBM Bob +48 \u2502\n\u2502 more (project directory not found) \u2502\n\u2502 \u2713 ./.agents/skills/prototype \u2502\n\u2502 universal: Amp, Antigravity, Antigravity CLI, Cline, Codex +19 more \u2502\n\u2502 symlinked: Claude Code, Eve \u2502\n[excerpt truncated]", "stderr": "", "needs_credentials": false, "needs_browser": false, "scope": "product operation" } } ], "safety": { "version": "z2x-1", "rules_version": "z2x-1", "summary": "Review signals: 7 known vulnerability.", "findings": [ { "kind": "known-vulnerability", "count": 7, "note": "OSV reports a known vulnerability in this dependency version.", "location_count": 1, "path": "js-yaml" } ], "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=mattpocock--skills-gpt-6-luna-1792785874620899102", "evidence_file": "/data/safety/mattpocock--skills-gpt-6-luna-1792785874620899102.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": 13, "native_bundle": null, "architecture": null, "backend": "hyperv", "platform_details": { "backend": "hyperv", "os": "linux" }, "platform_conflicts": null, "sandbox_source": null, "source_pin": { "commit": "5beb35b040e3de97e54fa9e386d7e42d15c295c2", "url": "https://github.com/mattpocock/skills" }, "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": 13, "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/mattpocock/skills", "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 README and package.json entry points; this repository distributes prompt-invoked skills and has no product scheduler or recurring cycle entry point.", "evidence": "Inspected README and package.json entry points; this repository distributes prompt-invoked skills and has no product scheduler or recurring cycle entry point.", "command": "" } ], "claims": [ { "kind": "claim", "claim": "The skills.sh install copies editable skills for the selected agent.", "source": "A plugin updates itself. [skills.sh](https://skills.sh/mattpocock/skills) copies editable files into your project, and you update them by hand. Pick one per agent, because installing both gives you every skill twice.", "input": "teach skill for Codex", "expected": "Installation complete", "command": "npx --yes skills@latest add mattpocock/skills --skill=teach --agent=codex --yes", "verdict": "yes", "outcome": "Real input produced the expected result: Installation complete", "evidence": "Installation complete\n\u001b[?25h\n\u2502\n\u25c7 Installed 38 skills \u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u256e\n\u2502 \u2502\n\u2502 \u2502\n\u2502 Mattpocock Skills \u2502\n\u2502 \u2713 ./.agents/skills/ask-matt \u2502\n\u2502 universal: Amp, Antigravity, Antigravity CLI, Cline, Codex +19 more \u2502\n\u2502 symlinked: Claude Code, Eve \u2502\n\u2502 skipped: AiderDesk", "returncode": 0, "source_checked": true, "source_file": "README.md" } ], "claims_note": null, "example_checks": [ { "kind": "example", "claim": "Install the teach skill for Codex via the documented skills.sh command.", "source": "README.md, Installation (30-second setup), Any other agent, or editable files", "input": "teach skill for Codex", "command": "npx --yes skills@latest add mattpocock/skills --skill=teach --agent=codex --yes", "evidence": "setup-pre-commit \u2502\n\u2502 universal: Amp, Antigravity, Antigravity CLI, Cline, Codex +19 more \u2502\n\u2502 symlinked: Claude Code, Eve \u2502\n\u2502 skipped: AiderDesk, AstrBot, Autohand Code CLI, Augment, IBM Bob +48 \u2502\n\u2502 more (project directory not found) \u2502\n\u2502 \u2502\n\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u256f\n\n\u2502\n\u2514 Done! Review skills before use; they run with full agent permissions.", "deferred": false, "expected": "Installation completes", "returncode": 0, "verdict": "yes", "outcome": "command completed successfully" } ], "does_what_it_says": "yes", "maintenance": { "archived": false, "commits_90d": 229, "last_commit_at": "2026-10-19T15:51:40Z", "last_release_at": "2026-10-04T12:48:18Z", "median_reply_hours": null, "merged_prs_90d": 73, "note": "actively maintained: last commit 4 days ago; 229 commits and 73 merged PRs in 90 days; 184 open issues, 17 open PRs; latest release 2026-10-04", "open_issues": 184, "open_prs": 17, "reply_share": null, "reply_threads": 0, "verdict": "maintained" }, "maintenance_verdict": "maintained", "maintenance_note": "actively maintained: last commit 4 days ago; 229 commits and 73 merged PRs in 90 days; 184 open issues, 17 open PRs; latest release 2026-10-04", "maintained": "active", "maintained_note": "last commit 1 days ago; 22 open issues, 14 answered or closed", "last_commit_at": "2026-10-22T09:35:28Z", "last_release_at": "2026-10-04T12:48:18Z", "open_issues": 22, "answered_issues": 14, "platforms_claimed": [ "linux" ], "topic": "agent-harness", "agent_interfaces": [ { "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": "2026-10-23T20:21:47.602841+00:00", "tested_commit": "5beb35b040e3de97e54fa9e386d7e42d15c295c2", "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": "mattpocock/skills", "source": "https://github.com/mattpocock/skills", "commit": "5beb35b040e3de97e54fa9e386d7e42d15c295c2", "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": "5beb35b040e3de97e54fa9e386d7e42d15c295c2", "url": "https://github.com/mattpocock/skills" }, "platform_details": { "os": "linux", "backend": "hyperv" }, "platform_conflicts": null, "reasoning": "low", "service_tier": "standard", "resources": { "cpus": 2, "memory_mib": 4096, "disk_mib": 32768 }, "operation": "Install a documented skills.sh skill into the project", "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/mattpocock--skills-gpt-6-luna-1792785874620899102.json" }