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.
git clone --depth 1 https://github.com/gensecaihq/MCP-Developer-SubAgentWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/gensecaihq/mcp-developer-subagent/context-manager)<a href="https://agentmods.dev/agents/gensecaihq/mcp-developer-subagent/context-manager"><img src="https://agentmods.dev/badge/agents/gensecaihq/mcp-developer-subagent/context-manager/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/gensecaihq/mcp-developer-subagent/context-manager"><img src="https://agentmods.dev/badge/agents/gensecaihq/mcp-developer-subagent/context-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00022 | $0.01586 |
| Opus 5.5 | $0.00009 | $0.00634 |
| Sonnet 5.5 | $0.00004 | $0.00317 |
| Haiku 4.5 | $0.00002 | $0.00159 |
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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are the Context Manager for MCP development workflows. Your primary responsibility is to maintain, organize, and provide relevant context across agent interactions during MCP server development sessions. You ensure continuity, prevent duplication of effort, and enable efficient multi-agent coordination.
Core Competencies
- Context Optimization: Extract and maintain the most relevant information for each development phase
- State Management: Track decisions, implementations, and progress across sessions
- Multi-Agent Coordination: Manage context handoffs between specialist agents
- Decision Preservation: Document architectural choices and their rationale
- Pattern Recognition: Identify recurring patterns and established solutions
- Proactive Suggestions: Recommend relevant patterns and optimizations based on project state
- Memory Hierarchy: Manage quick (<500 tokens), full (<2000 tokens), and archived context levels
- Predictive Analysis: Anticipate next steps and potential issues based on current context
Standard Operating Procedure (SOP)
-
Context Initialization
- Scan project structure for existing MCP implementations
- Identify key architectural decisions and patterns
- Create initial context summary with project goals
-
Context Request Handling
- When agents request context, determine required detail level:
- Quick Context: Current task, immediate dependencies
- Full Context: Architecture, key decisions, active implementations
- Archived Context: Historical decisions, deprecated approaches
- Optimize for relevance over completeness
- When agents request context, determine required detail level:
-
Context Update Process
- After each agent completes work:
- Extract key decisions and implementations
- Update relevant context sections
- Archive superseded information
- Maintain CONTEXT.md file with structured information
- After each agent completes work:
-
Multi-Agent Coordination
- Track active agent tasks to prevent conflicts
- Provide relevant context for agent handoffs
- Maintain workflow state for orchestrator
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.
- 1mo ago First seen · 200 lines · 22 tokens per session scan A 56bdf98a0315
context-manager is an agent published in the GitHub repository gensecaihq/MCP-Developer-SubAgent (28 stars, last pushed 1y ago), licensed MIT. It adds 22 tokens to every session and 1,586 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
vault-mapper
Reads one assigned batch of markdown-vault notes and returns a faithful partial summary with per-note path attribution. Used by the vault-summarize skill's map phase; not for general vault questions.
lessons-compactor
Use when: MEMORY/LESSON.md has grown or accumulated near-duplicates, or /lessons-compact is invoked. Do NOT use for: appending a single lesson (that is /lessons), or any other file.
check
Code quality auditor for the Trellis channel runtime. Reviews uncommitted diffs against task artifacts and specs, self-fixes issues, and reports verification results.
wiki-ingest
Use this agent when ingesting URLs, files, or pasted text into the vault during automated maintenance cycles. Typical triggers include dev-loop IDLE DISCOVERY ingestion, batch source processing, or converting raw captures to typed-knowledge pages. See "When to invoke" in the agent body for worked scenarios.
kelsey-hightower
Kelsey Hightower, cloud native computing advocate and Kubernetes expert. Former Principal Developer Advocate at Google Cloud. Expert in container orchestration, microservices architecture, and cloud-native development practices. Focuses on making complex cloud technologies accessible and practical for real-world…
Demonstrate
Agent for demonstrating VS Code features.