Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From rlm-claude-code
Analyzes RLM trajectory file at path (default: last), producing summary stats, event distribution, slow events, and errors.
npx claudepluginhub rand/rlm-claude-code --plugin rlm-claude-codeHow this command is triggered — by the user, by Claude, or both
Slash command
/rlm-claude-code:trajectoryThe summary Claude sees in its command listing — used to decide when to auto-load this command
Analyze an RLM trajectory file. ## Usage `/rlm-claude-code:trajectory [path]` — Analyze trajectory at path (default: last trajectory) ## Analysis Output ## Commands ## Debugging with Trajectories 1. **Capture**: Run with `--verbosity debug --export-trajectory /tmp/debug.json` 2. **Analyze**: `/trajectory /tmp/debug.json` 3. **Identify**: Find slow events, errors, or unexpected recursion 4. **Fix**: See docs/process/debugging.md for issue-specific guidance
/analyzeValidates and analyzes trace files (OTEL JSON or Claude Code JSONL) for cases like grounding, missed actions, goal drift, tool failures, and guardrail violations, tracking events persistently.
/tracesQueries and debugs MLflow traces from Gemini tool calls — search by errors, slow execution, or trace ID, and log human feedback scores.
/buidl-traceDisplays agent execution trace for the current loop session from trace.jsonl, rendering table of timestamps, events, agents, phases, cycles, details, plus summary of events, agents, and errors.
/analyzeRuns autonomous transcript analysis pipeline across sessions, spawning @transcript-analyst agent to query JSONL data, detect anti-patterns, and write structured findings to .planning/kaizen/analysis-{date}.md
/debugInvestigates errors in files or production issues using Logfire traces: finds recent exceptions, runs SQL queries on OpenTelemetry data, suggests code fixes, shares trace links.
Share bugs, ideas, or general feedback.
Analyze an RLM trajectory file.
/rlm-claude-code:trajectory [path] — Analyze trajectory at path (default: last trajectory)
Trajectory Analysis: /path/to/trajectory.json
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Summary:
Total events: 23
Max depth reached: 2
Recursive calls: 4
REPL executions: 8
Tool uses: 3
Duration: 34.2s
Estimated cost: $0.47
Event Distribution:
ANALYZE: 3
REPL_EXEC: 8
REASON: 6
RECURSE_START: 4
RECURSE_END: 4
TOOL_USE: 3
FINAL: 1
Slow Events (>5s):
[12] RECURSE depth=1: 8.3s - "Analyze auth error handling..."
[18] TOOL_USE: 5.1s - bash: npm test
Errors: None
# Pretty-print trajectory
uv run python -m src.tools.trajectory_viewer trajectory.json
# Filter by depth
uv run python -m src.tools.trajectory_viewer trajectory.json --depth 1
# Filter by type
uv run python -m src.tools.trajectory_viewer trajectory.json --type repl_exec
# Compare two trajectories
uv run python -m src.tools.trajectory_diff working.json failing.json
# Export to HTML
uv run python -m src.tools.trajectory_viewer trajectory.json --html > trajectory.html
--verbosity debug --export-trajectory /tmp/debug.json/trajectory /tmp/debug.json