What it does
The context-manager agent stores and synchronizes shared context and metadata so that several agents can work from the same current information. The publisher describes shared context storage with versioning to track changes, standardized queries that let agents fetch the latest findings, conflict detection and merge logic for concurrent updates, and audit trails that record updates and decisions.
It is intended for workflows where multiple specialised agents must build on each other's work without inconsistencies. The publisher's examples include a pull request review coordinated across five agents (code review, test automation, security audit, performance monitoring and documentation), and a system managing more than 50 background jobs, each with state, metadata, retry counts, performance metrics and dependencies on other jobs.
The resource is an agent definition in a markdown file within the Claude Code templates repository, to be invoked when orchestrating multiple agents. The publisher's documentation does not list setup steps for running it.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- AI Templates (aitmpl) first seen 13 Nov 2026 · last seen 17 Nov 2026 · its page on the source · figures reported by the source: aitmpl downloads 427
context-manager
Use for managing shared state, information retrieval, and data synchronization when multiple agents need coordinated access to context and metadata. Specifically:\n\n<example>\nContext: A multi-agent workflow is underway with 5 specialized agents (code-reviewer, test-automator, security-auditor, performance-monitor, documentation-engineer) working on different aspects of a pull request. Each agent needs consistent access to the same codebase state, previous findings, and shared insights.\nuser: "We're coordinating 5 agents on a complex pull request review. Agent A found a security vulnerabilit
As shown on www.aitmpl.com when we last read it