Agent harness logs
Skill NetFabric/intelligentium/.agents/skills/agent-harness-logs
Find, inspect, query, redact, and troubleshoot logs, transcripts, sessions, and OpenTelemetry data from coding-agent harnesses on Windows, macOS, Linux, and WSL. USE FOR: GitHub Copilot in VS Code; Copilot CLI; Claude Code; OpenAI Codex; Gemini CLI; OpenCode; Cursor, Windsurf, Kiro, or other VS Code-family editors; locating log files; diagnosing tool or model failures; correlating turns, subagents, and tool calls; querying JSONL, plaintext, or SQLite without spending model tokens; preparing sanitized diagnostics. DO NOT USE FOR: application logs unrelated to coding agents; uploading raw logs; treating unstable transcript schemas as public APIs.From its SKILL.md
npx -y skills add NetFabric/intelligentium --skill agent-harness-logsAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
3.5 KB, as published. Nobody here has run it
Agent Harness Logs
Harnesses expose three different evidence surfaces. Identify the surface before querying it.
| Surface | Typical content | Best use |
|---|---|---|
| Operational/debug log | Startup, extensions, network, retries, crashes | Why the harness failed |
| Session/transcript | Prompts, responses, tools, turn graph | What happened in one interaction |
| OpenTelemetry | Structured events, metrics, traces | Fleet analysis and durable observability |
Workflow
- Read references/concepts-and-safety.md; never upload or paste an unreviewed log.
- Identify the harness and artifact in references/path-matrix.md.
- Load the matching reference: VS Code and editors, Copilot CLI and Claude Code, or Codex, Gemini CLI, and OpenCode.
- Run
python3 scripts/harness_logs.py discover --toon, then inventory the smallest relevant root with--toon. - Query locally using references/query-recipes.md. Use
--toonfor model-bound output; stream source files and never read a large log wholesale. - Correlate with stable IDs when available: session, turn, prompt, request, tool-call, span, and parent-span IDs.
- Redact to a new file, inspect the result manually, then share only the minimum slice needed.
- State harness version, OS, artifact type, time window, and whether a path is documented or discovered.
Script
scripts/harness_logs.py uses the Python standard library for queries and the official @toon-format/cli through npx when --toon is requested. It discovers candidate roots, inventories files, streams regex searches, summarizes JSONL fields, runs read-only SQLite queries, and creates best-effort redacted copies. Structured commands retain JSON/JSONL when --toon is omitted. The script never invokes a model.
References
| File | Load when |
|---|---|
| references/concepts-and-safety.md | Handling sensitive data, large files, or unstable schemas |
| references/path-matrix.md | Locating artifacts across operating systems |
| references/vscode-and-editors.md | Troubleshooting Copilot in VS Code or VS Code-family editors |
| references/copilot-and-claude.md | Inspecting Copilot CLI or Claude Code |
| references/codex-gemini-opencode.md | Inspecting Codex, Gemini CLI, or OpenCode |
| references/query-recipes.md | Running deterministic, zero-token queries |
| references/sources.md | Verifying claims or updating version-sensitive details |