yeaight7/agent-powerups / plugins/dev-vitals/skills/agent-session-forensics
agent-session-forensics
VerifiedUse when diagnosing agent session history, interrupted tool loops, missing tool results, timing bottlenecks, or subagent trace correlation.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 3.1 KB |
| references/history-diagnostics.md | markdown | 1.3 KB |
references/history-diagnostics.md
View on GitHub# Session History Diagnostics
## Read-Only First
Never edit history before:
- locating session dir
- backing up target JSON
- finding last valid tool-call boundary
- getting user approval for mutation
## Inspection Queries
```bash
jq '.messages | length' history.json
jq '.messages[-5:] | .[] | {role, stop_reason, has_tool_calls: (.tool_calls != null), has_tool_results: (.tool_results != null)}' history.json
jq '.messages | to_entries | .[] | {index: .key, role: .value.role, tool_calls: (.value.tool_calls | keys? // []), tool_results: (.value.tool_results | keys? // [])}' history.json
```
## Failure Patterns
| Pattern | Symptom | Fix |
| --- | --- | --- |
| unanswered tool call | assistant has `tool_calls`, no following result | truncate to last valid result after backup |
| duplicate user turn | two user messages before assistant | inspect interruption/resume boundary |
| malformed tool result | result id missing or mismatched | repair only exact id if approved |
| slow loop | repeated tool timing spikes | summarize tool count/durations |
| stale session | history references missing files | restart with compact handoff |
## Report Shape
```text
Session:
Files inspected:
Message count:
Last valid boundary:
Tool-call mismatches:
Slowest calls:
Likely cause:
Recommended repair:
Mutation required: yes/no
```
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |