Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add rjmurillo/ai-agents/plugin install project-toolkitWrote 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/skills/rjmurillo/ai-agents/context-hub-setup)<a href="https://agentmods.dev/skills/rjmurillo/ai-agents/context-hub-setup"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/context-hub-setup.svg" alt="Measured on agentmods" 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 | $0.00033 | $0.00824 |
| Opus 5 | $0.00016 | $0.00412 |
| Sonnet 5 | $0.00007 | $0.00165 |
| Haiku 4.5 | $0.00003 | $0.00082 |
Grade A, and why
context-hub-setup 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 yesterday.
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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Hub Setup
Check the plugins the context commands depend on, and report what is missing.
Prerequisites
Context Hub requires these plugins to be installed:
- Serena - Symbol-level code analysis and the
.serena/memories/store (required for/encode-repo-serena) - Context7 - Framework documentation (recommended for
/context-gather)
Step 1: Check Plugin Prerequisites
First, check if the required plugins are installed:
claude plugins list
Look for:
serenaor similar (for code analysis)context7or similar (for framework docs)
If Serena is not installed:
To use /encode-repo-serena, install the Serena plugin:
claude plugins install serena
Or search for it in the marketplace:
claude plugins search serena
If Context7 is not installed:
For framework documentation in /context-gather, install Context7:
claude plugins install context7 --marketplace pleaseai/claude-code-plugins
Or search for it:
claude plugins search context7
Step 2: Verify Complete Setup
Report status of all components:
Context Hub Setup Status:
-------------------------
Serena Plugin: [Installed / Not installed - run: claude plugins install serena]
Context7 Plugin: [Installed / Not installed - run: claude plugins install context7 --marketplace pleaseai/claude-code-plugins]
Commands available:
- /context-gather - Multi-source context retrieval
- /encode-repo-serena - Repository encoding (requires Serena)
Memory search reads committed files rather than querying a server:
uv run python "${COPILOT_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT:-.claude}}/skills/memory/scripts/search_memory.py" "topic"
It reads the markdown under .serena/memories/, so it works whether or not the
Serena MCP server is reachable. The plugin-root prefix resolves the script in a
vendored install, where a bare .claude/ path does not exist.
Step 3: Quick Test (Optional)
Offer to test the setup:
Test Serena (if installed):
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.
- yesterday Changed · -62 lines · +1 tokens per session b104f0124eea
- 2d ago First seen · 185 lines · 32 tokens per session scan A 8a2ee23aef52
context-hub-setup is a skill published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed today), licensed MIT. It adds 33 tokens to every session and 824 once invoked, about $0.0002 per session on Opus 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 2026-09-03.
Other skills, from other repositories
ci-cd
GitHub Actions CI/CD 파이프라인 설계 및 자동화.
github-release-management
Comprehensive GitHub release orchestration with AI swarm coordination for automated versioning, testing, deployment, and rollback management.
devops-assistant
Assists in version control, deployment, and automation tasks, ensuring smooth DevOps operations and workflow efficiency.
openclaw-control
控制和管理 OpenClaw AI 助手。用于发送消息给 OpenClaw、检查状态、管理配置和安装技能。当用户想要与 OpenClaw 交互或管理 OpenClaw 时使用此技能。.
azure-deployment-operations
Production deployment patterns for Azure Static Web Apps, Container Apps, App Service, and infrastructure.
azure-devops-automation
CI/CD pipelines, infrastructure as code, and deployment automation for Azure workloads.