jq-for-clawd
Query Claude Code session history using jq to find past conversations. Use when users mention "JQ for Claude", "jq4clawd", "jq-for-clawd", "find my past sessions", "what did I ask before", "search conversation history", or "query session files".
What this skill does
# JQ for Claude - Session History Queries
Use this skill when users ask about past conversations, previous sessions, or conversation history.
---
## Session File Location
Claude Code stores session history as JSONL files at:
```
~/.claude/projects/<encoded-project-path>/<session-id>.jsonl
```
**Path encoding**: Project paths use dashes instead of slashes.
- `/home/user/my-project` becomes `-home-user-my-project`
### Find the Project Directory
To find sessions for a specific project path:
```bash
# Encode project path (replace / with -)
PROJECT_PATH="/home/user/my-project"
ENCODED=$(echo "$PROJECT_PATH" | sed 's|^/|-|; s|/|-|g')
SESSION_DIR="$HOME/.claude/projects/$ENCODED"
# List sessions sorted by modification time
ls -lt "$SESSION_DIR"/*.jsonl 2>/dev/null | head -10
```
### List All Project Directories
```bash
ls -lt ~/.claude/projects/ | head -20
```
---
## JSONL File Structure
Each session file contains one JSON object per line:
| Line Type | Key Fields | Description |
|-----------|------------|-------------|
| `summary` | `type`, `summary`, `leafUuid` | Session metadata (first line) |
| `user` | `type`, `timestamp`, `message` | User messages |
| `assistant` | `type`, `timestamp`, `message` | Claude responses |
| `system` | `type`, `message` | System prompts |
| `file-history-snapshot` | `type`, `snapshot` | File state snapshots |
### Message Content Structure
User and assistant messages have this structure:
```json
{
"type": "user",
"timestamp": "2026-01-10T22:32:07.522Z",
"message": {
"role": "user",
"content": "your message text here"
},
"sessionId": "uuid",
"uuid": "message-uuid"
}
```
**Note**: `message.content` can be either:
- A string: `"content": "hello"`
- An array: `"content": [{"type": "text", "text": "hello"}]`
---
## Common jq Patterns
### Extract User Messages with Timestamps
```bash
cat session.jsonl | jq -r '
select(.type == "user") |
.timestamp + " | " + (
if .message.content | type == "string"
then .message.content[0:300]
else (.message.content[0].text // "N/A")[0:300]
end
)
' | grep -v "N/A" | grep -v "command-name" | grep -v "local-command"
```
### Count Message Types in a Session
```bash
cat session.jsonl | jq -r '.type' | sort | uniq -c
```
### Get Session Start Time
```bash
head -5 session.jsonl | jq -r 'select(.type == "user") | .timestamp' | head -1
```
### Find Sessions by Content
Search across all sessions in a project for a keyword:
```bash
SESSION_DIR="$HOME/.claude/projects/-home-user-my-project"
for f in "$SESSION_DIR"/*.jsonl; do
if grep -q "keyword" "$f" 2>/dev/null; then
echo "=== $f ==="
cat "$f" | jq -r 'select(.type == "user" and (.message.content | tostring | test("keyword"; "i"))) | .timestamp + " | " + (.message.content | tostring)[0:200]' 2>/dev/null
fi
done
```
### List Recent Sessions with First User Message
```bash
SESSION_DIR="$HOME/.claude/projects/-home-user-my-project"
for f in $(ls -t "$SESSION_DIR"/*.jsonl 2>/dev/null | grep -v "agent-" | head -5); do
echo ""
echo "=== $(basename $f) ==="
cat "$f" | jq -r '
select(.type == "user") |
.timestamp + " | " + (
if .message.content | type == "string"
then .message.content[0:150]
else (.message.content[0].text // "N/A")[0:150]
end
)
' 2>/dev/null | grep -v "N/A" | grep -v "command-name" | head -3
done
```
---
## Filtering Tips
### Exclude Agent Sessions
Agent/subagent sessions have filenames starting with `agent-`:
```bash
ls -lt "$SESSION_DIR"/*.jsonl | grep -v "agent-"
```
### Filter by Date
Sessions include ISO timestamps. Filter with jq:
```bash
cat session.jsonl | jq -r '
select(.type == "user" and .timestamp > "2026-01-10") |
.timestamp + " | " + (.message.content | tostring)[0:100]
'
```
### Exclude System Messages
Filter out command invocations and system noise:
```bash
grep -v "command-name" | grep -v "local-command" | grep -v "N/A"
```
---
## Example Workflow
When a user asks "what did I ask you in our last few sessions?":
1. **Identify the project path** (current working directory or ask user)
2. **Encode and locate sessions**:
```bash
ENCODED=$(echo "$PWD" | sed 's|^/|-|; s|/|-|g')
SESSION_DIR="$HOME/.claude/projects/$ENCODED"
```
3. **List recent non-agent sessions**:
```bash
ls -lt "$SESSION_DIR"/*.jsonl | grep -v "agent-" | head -5
```
4. **Extract user messages from each**:
```bash
cat "$SESSION_DIR/<session-id>.jsonl" | jq -r '
select(.type == "user") |
.timestamp + " | " + (
if .message.content | type == "string"
then .message.content[0:300]
else (.message.content[0].text // "N/A")[0:300]
end
)
' | grep -v "N/A" | grep -v "command-name" | head -5
```
5. **Present results** in a clean, organized format grouped by session with timestamps.
---
## Troubleshooting
**No sessions found**: Verify the project path encoding matches exactly. Check `ls ~/.claude/projects/` for the correct directory name.
**jq parse errors**: Some lines may have malformed JSON. Add `2>/dev/null` to suppress errors.
**Empty content**: Some user messages (like tool approvals) have array content without text. Filter with `grep -v "N/A"`.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.