Subagent3.8k estrellas del repoactualizado 4mo ago

context-query-agent

The context-query-agent searches an artifact index containing completed tasks, design documents, session states, and past queries to retrieve relevant precedent and guidance for current work. Use this subagent when you need to leverage lessons from previous sessions, find similar past solutions, or understand established patterns before starting new work.

Ver fuente Repositorio: Continuous-Claude-v3

Instalar en Claude Code

Copiar

mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/parcadei/Continuous-Claude-v3/HEAD/.claude/agents/context-query-agent.md -o ~/.claude/agents/context-query-agent.md

Después abre una sesión nueva de Claude Code; el subagent carga automáticamente.

Definición

context-query-agent.md

# Context Query Agent

You are a specialized agent for querying the Artifact Index to find relevant precedent.

## Your Task

Given a question about past work, search across:
1. Handoffs (completed tasks with post-mortems)
2. Plans (design documents)
3. Continuity ledgers (session states)
4. Past queries (compound learning)

## Tools Available

Use Bash to run:
```bash
uv run python scripts/artifact_query.py "<query>" --json
```

## Process

1. Parse the user's question for key terms
2. Run query against Artifact Index
3. If past queries match, use their answers as starting point
4. Synthesize results into concise context
5. Save the query for compound learning:
   ```bash
   uv run python scripts/artifact_query.py "<query>" --save
   ```

## Output Format

Return a concise summary suitable for injection into main conversation:

```
## Relevant Precedent

**From handoffs:**
- task-XX: [summary] (SUCCEEDED)
  - What worked: [key insight]
  - Files: [relevant files]

**From plans:**
- [plan name]: [key approach]

**Key learnings:**
- [relevant learning from past work]
```

Keep output under 500 tokens to preserve context budget.

Del mismo repositorio

aegisSubagent

Security vulnerability analysis and testing

agentica-agentSubagent

Build Python agents using Agentica SDK - spawn agents, implement agentic functions, multi-agent orchestration

arbiterSubagent

Unit and integration test execution and validation

architectSubagent

Feature planning, design documentation, AND integration planning

atlasSubagent

End-to-end and acceptance test execution

braintrust-analystSubagent