context-synthesizer — Claude Code subagent: usage and setup
context-synthesizer synthesizes multidimensional context across task constraints, domain patterns, and past execution memory. Helps maintain clear situational awareness during complex execution.
no license ★ 850 updated 2026-10-26
.claude/agents/context-synthesizer.mdWhat context-synthesizer does
This subagent aggregates distinct information layers: the immediate task with its constraints, domain-level practices, agent state, and historical execution records. Lifecycle hooks invoke agentic-flow through npx before and after execution to query and update the reasoningbank storage.
Relevance filtering uses weighted scoring across four factors: task alignment accounts for 40%, reliability takes 25%, actionability gets 20%, and recency contributes 15%. Items below the 0.6 threshold get pruned, keeping at most 20 entries per category to avoid context bloat.
Without Node.js and an accessible npx binary in the environment, the pre- and post-execution hooks will fail during memory retrieval.
What it helps with
- Consolidate fragmented task requirements and domain knowledge into one brief
- Filter out irrelevant historical memories using weighted scoring criteria
- Retrieve past failure modes and patterns from
reasoningbank - Prepare structured risk warnings and execution strategies for peer agents
Example prompts for the agent
- Synthesize context for refactoring the authentication layer using past project memories.
- Gather domain best practices and environmental constraints before tackling this migration.
- Analyze previous task outcomes and build an execution summary for this feature.
How to install context-synthesizer
Manually: put the files in place
.claude/agents/context-synthesizer.mdFor all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention
Manually: put the files in place
.codex/agents/context-synthesizer.tomlCodex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/
Manually: put the files in place
.cursor/agents/context-synthesizer.mdCursor also reads .claude/agents/
Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean
Questions about context-synthesizer
How to install context-synthesizer in Claude Code?
Place the subagent configuration into .claude/agents/context-synthesizer.md in your project root. Claude Code will load the subagent automatically.
What does context-synthesizer do?
It aggregates task goals, technical constraints, and past execution data into an actionable summary. Peer agents use this distilled view to avoid known pitfalls and stay aligned with domain standards.
What external dependencies does context-synthesizer rely on?
Its pre and post hooks require npx to execute the agentic-flow package for querying and distilling data in reasoningbank.