context-query-agent

Why this score

This repo hosts 32 subagents, so its 3,946 stars are split between them (about 123 each) for scoring.

Popularity score: 53/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank

What it can use

• ! Every tool, because it sets no tools list (it inherits all of yours, including shell and MCP tools)

Model: sonnet

This agent can act outside your files. Read it before installing, and narrow its tools: line if it needs less.

The agent file

---
name: context-query-agent
description: Query the artifact index for precedent and guidance
model: sonnet
---

# 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.

MIT license, from parcadei/Continuous-Claude-v3 at commit d07ff4b06b62.

Security

Scanned Oct 21, 2026 at commit d07ff4b06b62, with Cisco's open-source skill-scanner.

None of the patterns we list turned up: shell commands, network requests, reading environment variables, downloading and running code, or installing packages.

A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan

Alternatives

Other makers' add-ons that do the same job, next to this one.