// Session history search — INVOKE before planning, before web research, after errors, or when looking for past conversation content. Use INSTEAD of manually grepping .jsonl session files.
| name | claude-historian |
| description | Session history search — INVOKE before planning, before web research, after errors, or when looking for past conversation content. Use INSTEAD of manually grepping .jsonl session files. |
| triggers | ["PreToolUse","PostToolUseFailure"] |
Session memory. Use INSTEAD of grepping .jsonl files manually. Checks past sessions before redundant research, planning, or debugging.
| Hook | When | Action |
|---|---|---|
| PreToolUse(WebSearch/WebFetch) | Before web research | Checks search(scope="similar") first |
| PostToolUseFailure(Bash/Edit) | After tool errors | Suggests search(scope="errors") |
| Command | Description |
|---|---|
/search-historian <query> | Search past sessions for solutions, decisions, context |
search(query, scope)One tool, many scopes:
| Scope | What It Finds | When to Use |
|---|---|---|
conversations | Full-text across all sessions | General search |
similar | Related past questions | Before web research |
errors | How errors were previously fixed | After tool failures |
plans | Past implementation plans | Before planning |
files | File changes across sessions (needs filepath) | Before editing familiar files |
tools | Successful tool workflows | Before launching agents |
sessions | Recent work sessions | Browse history |
config | .claude rules, skills, agents | Config troubleshooting |
tasks | Task management data | Check past tasks |
memories | Saved memories | Cross-session memory |
inspect(session_id)Deep summary of a specific session with key insights.
search(query="feature name", scope="plans")
search(query="topic", scope="similar")
If found: use past results, skip web search.
search(query="error message", scope="errors")
If found: apply previous solution.
search(query="topic", scope="conversations")
search(scope="files", filepath="path/to/file")
search(scope="sessions")
Automatic tool discovery across 19 sources — INVOKE before planning, before adding dependencies, or when looking for tools to discover relevant skills, plugins, and MCP servers
Use after writing or editing a plan file, after exiting plan mode, or when asked "why did you choose this?" — surfaces decisions, risks, and blind spots before implementation.
Continuous learning — INVOKE after sessions with many errors or corrections to record patterns and improve rules, hooks, and skills
Cross-session memory - save insights after research, restore context at session start. Reduces re-exploration and prevents token waste.
File checkpoint and recovery — auto-quicksaves before destructive commands, INVOKE before implementing a plan or starting risky multi-file changes. Also use when user asks to undo changes or compare current state to a prior checkpoint.
Prompt rhetoric coach — deterministic scoring and restructuring using Anthropic best practices