NetFabric/NetFabric.Numerics / .agents/skills/agent-harness-logs
agent-harness-logs
VerifiedFind, 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.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 3.5 KB |
| references/codex-gemini-opencode.md | markdown | 3.2 KB |
| references/concepts-and-safety.md | markdown | 2.5 KB |
| references/copilot-and-claude.md | markdown | 2.8 KB |
| references/path-matrix.md | markdown | 3.2 KB |
| references/query-recipes.md | markdown | 2.9 KB |
| references/sources.md | markdown | 2.0 KB |
| references/vscode-and-editors.md | markdown | 2.4 KB |
| scripts/harness_logs.py | script | 10.3 KB |
| scripts/test_harness_logs.py | script | 4.5 KB |
references/concepts-and-safety.md
View on GitHub# Concepts and Safety
## Choose the Right Artifact
| Question | Artifact |
| --- | --- |
| Did startup, auth, networking, an extension, or a subprocess fail? | Operational/debug log |
| Which prompt caused a tool call, response, or edit? | Session/transcript |
| How much time, cost, or token use occurs across users and sessions? | OpenTelemetry metrics/events |
| Where did latency occur in a turn? | OpenTelemetry traces or correlated request/tool timing |
A transcript is not merely a debug log. It can contain the full conversation, tool arguments and results, file contents, system prompts, and repository paths. An OTEL event stream may redact content by default but still include identity, model, timing, cost, and session identifiers.
## Safe Procedure
1. Record harness version and OS before interpreting a schema.
2. Inspect file names, sizes, and modification times before content.
3. Narrow by session ID, timestamp, event type, request ID, or error text.
4. Keep analysis local with `jq`, `rg`, PowerShell, SQLite, or the bundled script.
5. Redact into a different file. Never overwrite the only evidence copy.
6. Manually review the redacted result; pattern redaction is best effort, not proof of safety.
7. Share a minimal excerpt, not an entire state directory.
## Sensitive Fields
Assume these are sensitive even when a harness calls them diagnostics:
- Prompts, responses, system prompts, summaries, and hidden context
- Tool inputs/outputs, shell commands, file contents, diffs, and paths
- Authorization headers, cookies, API keys, OAuth tokens, and MCP credentials
- User email, account/organization IDs, installation IDs, and session IDs
- Repository names, remote URLs, issue/PR content, and environment variables
- Heap snapshots and raw API request/response bodies
## Schema Stability
Operational logs and transcript JSONL are often implementation details. Prefer documented CLI exports or OTEL schemas for automation. When querying internal JSONL:
- Probe keys before writing a filter.
- Tolerate missing and additional fields.
- Do not assume one harness's `type`, `role`, or `message` shape applies to another.
- Treat joins between transcript fields and telemetry IDs as version-specific unless documented.
## Large Files
Use streaming commands. Avoid `cat` on large files, loading complete JSONL into memory, opening SQLite as text, or passing raw logs to a model. Start with byte size, modification time, and line count; then inspect matching lines with a hard result limit.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| deprecation-and-migrationaddyosmani/agent-skillsManages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when migrating a database schema in production, such as renaming or dropping a column without downtime (expand/contract). Use when deciding whether to maintain or sunset existing code. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| performance-optimizationaddyosmani/agent-skillsOptimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| agent-cost-reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |
| agent-cost-reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |