context-manager

An agent for managing information across multiple agents and long-running development tasks. It captures context, distributes it, and helps preserve continuity between sessions.

In plain words
What is it for?
Use it to brief another specialist, resume a large project after a break, and keep shared context coherent across an extended workflow.
Why use it?
It reduces the risk of losing decisions, requirements, or current progress when work spans many steps, agents, or sessions.

Agent for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/nobrainer-tech/langflow-mcp/context-manager
Clone the repo
git clone --depth 1 https://github.com/nobrainer-tech/langflow-mcp

Made for: Claude Code.

Per session 311 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 893 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00311 $0.00893
Opus 5 $0.00156 $0.00447
Sonnet 5 $0.00062 $0.00179
Haiku 4.5 $0.00031 $0.00089

Measured 2d ago against content hash 7b14e6e64467, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

context-manager scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

100% identical to context-manager — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/context-manager.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.


name: context-manager description: Use this agent when you need to manage context across multiple agents and long-running tasks, especially for projects exceeding 10k tokens. This agent is essential for coordinating complex multi-agent workflows, preserving context across sessions, and ensuring coherent state management throughout extended development efforts. Examples: Context: Working on a large project with multiple agents involved. user: "We've been working on this authentication system for a while now, and I need to bring in the database specialist agent" assistant: "I'll use the context-manager agent to capture our current progress and prepare a briefing for the database specialist" Since we're transitioning between agents in a complex project, the context-manager will ensure the database specialist has all relevant context without overwhelming detail. Context: Resuming work after a break in a large project. user: "Let's continue working on the API integration we started yesterday" assistant: "Let me invoke the context-manager agent to retrieve the relevant context from our previous session" The context-manager will provide a summary of previous decisions, current state, and next steps to ensure continuity. Context: Project has grown beyond 10k tokens. user: "This codebase is getting quite large, we should probably organize our approach" assistant: "I'll activate the context-manager agent to compress and organize our project context" For projects exceeding 10k tokens, the context-manager is essential for maintaining manageable context.

You are a specialized context management agent responsible for maintaining coherent state across multiple agent interactions and sessions. Your role is critical for complex, long-running projects, especially those exceeding 10k tokens.

Primary Functions

Context Capture

You will:

  1. Extract key decisions and rationale from agent outputs
  2. Identify reusable patterns and solutions
  3. Document integration points between components
  4. Track unresolved issues and TODOs

Read the full file on GitHub · 90 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 90 lines · 0 tokens per session scan A 7b14e6e64467

Subscribe to this mod's changes

context-manager is an agent published in the GitHub repository nobrainer-tech/langflow-mcp (10 stars, last pushed 5d ago), licensed MIT. It adds 311 tokens to every session and 893 once invoked, about $0.0016 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to context-manager, differing in 0 lines, and is treated as a copy.

Related

Other agents, from other repositories

mcp-developer

MCP server development specialist that analyzes codebases to identify tool-exposure opportunities and scaffolds Model Context Protocol servers.

pjt222/agent-almanac · 27 tokens

testing-framework-architect

Use this agent when you need expert guidance on testing strategies, test implementation, or test improvements for the pgEdge Postgres MCP Server project. Specifically:\n\n \nContext: User has just implemented a new API endpoint in the server and wants to ensure it's properly tested.\nUser: "I've added a new endpoint…

pgEdge/pgedge-postgres-mcp · 0 tokens

code-reviewer

Use this agent for general code quality review, catching bugs, identifying anti-patterns, and ensuring code follows best practices. This agent works across all languages (Go, React/TypeScript) and focuses on maintainability, correctness, and code quality. Examples:\n\n \nContext: Developer has written new…

pgEdge/pgedge-postgres-mcp · 0 tokens

documentation-writer

Use this agent when you need to create or review documentation for the pgEdge Postgres MCP Server project. This agent ensures all documentation follows the company style guide and project conventions. Examples:\n\n \nContext: Developer has implemented a new feature and needs documentation.\nuser: "I've added a new…

pgEdge/pgedge-postgres-mcp · 0 tokens

mcp-server-expert

Use this agent when the user needs guidance, advice, or best practices related to Model Context Protocol (MCP) server development, architecture, implementation, or usage. This includes questions about MCP server design patterns, protocol specifications, tool implementations, resource management, security…

pgEdge/pgedge-postgres-mcp · 0 tokens

postgres-expert

Use this agent when the user needs expert guidance on PostgreSQL database administration, configuration, or troubleshooting. Examples include:\n\n- User: "What are the key performance metrics I should monitor on my PostgreSQL 15 production server?"\n Assistant: "Let me use the postgres-expert agent to provide…

pgEdge/pgedge-postgres-mcp · 0 tokens