aviz85/search-history
plugins/search-history/skills/search-history/SKILL.md
Search across all Claude Code conversation history (JSONL files) across all projects.
$ install --global
skillsauthnpx skillsauth add aviz85/claude-skills-library search-historyInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 3, 2026, 12:15 PM17.5s2 files scanned
SKILL.md
- name:
- search-history
- description:
- Search across all Claude Code conversation history (JSONL files) across all projects.
- version:
- 1.0.0
- author:
- aviz85
Search Claude Code Conversation History
Search across all Claude Code sessions and projects to find past discussions, solutions, and context.
Usage
/search-history "aviz-museum" /search-history "supabase migration" --project Users-aviz-dreemz-backend /search-history "Riley Brown" --user-only --limit 5
Parameters
<search-term>-- keyword or phrase to search (required)--project <name>-- limit to specific project dir (e.g., -Users-aviz-sb)--user-only-- only search user messages (skip assistant/progress/system)--limit N-- max sessions to show (default: 10)
How It Works
Storage Structure
~/.claude/projects/
-Users-aviz-sb/ # Project dir (path with / -> -)
ae1972bf-...-2e6f1b34be03.jsonl # Session file (UUID)
ae1972bf-.../ # Session artifacts
subagents/ # Subagent logs
tool-results/ # Tool output files
-Users-aviz-dreemz-backend/
...
JSONL Message Types
Each line is a JSON object with a type field:
| Type | Description | Key Fields |
|------|-------------|------------|
| user | User input | message.content (string or array), timestamp, cwd |
| assistant | Claude response | message.content (array of text/tool_use blocks), message.model |
| progress | Tool execution tracking | data.toolName, data.status |
| system | System events | Compaction, boundaries |
| file-history-snapshot | File backup metadata | snapshot.timestamp |
| queue-operation | Inbox operations | operation |
| last-prompt | Last user prompt text | prompt |
Content Extraction
- User messages:
message.contentis usually a string, sometimes array of content blocks. - Assistant messages:
message.contentis array -- extract.textfromtype: "text"blocks.
Implementation
Search using grep + Python for structured output:
# Quick grep across all projects
grep -rl "SEARCH_TERM" ~/.claude/projects/*/*.jsonl
For structured search with context, use Python to parse JSONL files, extract matching messages, and display with session metadata (project, timestamp, message type).
Tips
- Start broad -- grep is fast across all JSONL files
- Use
--user-onlyto find what YOU asked, not what Claude replied - Use
--projectto narrow to a specific workspace - Session UUIDs can be used with
claude --resume SESSION_ID - Tool results are in separate
.txtfiles undersession-dir/tool-results/ - Subagent conversations are in
session-dir/subagents/agent-*.jsonl
Related Skills
aviz85/ten-by-ten
development
VerifiedTrustedCommunity
The 10x10 method — generate breadth, then converge with human judgment. Use whenever a single AI output won't nail it and quality matters (design, copy, naming, posters, messaging, strategy options, code approaches), OR when the user says '10x10', 'ten by ten', 'give me 10 options', 'show me variations', or asks to refine/tighten an output instead of round-after-round corrections.
41SKILL.mdUpdated Jun 11, 2026
aviz85/ten-by-ten
development
VerifiedTrustedCommunity
The 10x10 method — generate breadth, then converge with human judgment. Use whenever a single AI output won't nail it and quality matters (design, copy, naming, posters, messaging, strategy options, code approaches), OR when the user says '10x10', 'ten by ten', 'give me 10 options', 'show me variations', or asks to refine/tighten an output instead of round-after-round corrections.
41SKILL.mdUpdated Jun 11, 2026
aviz85/reality-check
development
VerifiedTrustedCommunity
Deep code audit that detects misleading patterns — fake tests, mock abuse, shallow health checks, overly optimistic error handling, hidden debt. Produces a structured report with findings AND actionable recommendations. Use when code looks green but smells wrong.
41SKILL.mdUpdated Jun 11, 2026
aviz85/quick-voice
tools
VerifiedTrustedCommunity
Spin up an instant browser voice session (OpenAI Realtime gpt-realtime-2) to close a topic in a short conversation instead of working through documents. Generic & white-label - works for any process. Supports live data work (read/update files, JSON, run commands), and distill mode (no tools, ends with a structured deliverable). Has a generic canvas that can display images, markdown, code, html, json, video, audio - perfect for "let's go over X" flows where the agent shows you items one by one and you react in real time. Use when user says "let's close this in a voice call", "run a quick voice session about X", "תפעיל שיחה קולית", "let's go over the [images/leads/PRs/files/notes]", or when a task is faster as a 3-minute conversation than as a document edit.
41SKILL.mdUpdated Jun 11, 2026