mcpkernel: Skill for Claude Code

.github/skills/research-and-improve/SKILL.md

research-and-improve is a skill for Claude Code, Codex from piyushptiwari1/mcpkernel. It costs 48 tokens per session (441 once invoked), scanned A, original, Apache-2.0.

A workflow for researching current security and Python engineering techniques, evaluating them against MCPKernel, implementing suitable improvements and documenting the results. MCP is a standard for connecting AI agents to tools and data.

In plain words
What is it for?
Use it when upgrading MCPKernel’s security, asynchronous Python code, sandboxing, taint tracking or protocol support, including research, tests, implementation and documentation.
Why use it?
It provides a repeatable path for deciding whether new security, performance or protocol approaches fit the existing code without breaking its interfaces.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

This is piyushptiwari1/mcpkernel's own configuration. It tells Claude Code and Codex how to work on mcpkernel itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcpkernel configures →

Reuse

Borrowing it

Nothing to install: this file belongs to piyushptiwari1/mcpkernel. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/piyushptiwari1/mcpkernel/main/.github/skills/research-and-improve/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/piyushptiwari1/mcpkernel

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for research-and-improve

README.md
[![agentmods](https://agentmods.dev/badge/skills/piyushptiwari1/mcpkernel/research-and-improve/github.svg)](https://agentmods.dev/skills/piyushptiwari1/mcpkernel/research-and-improve)
Your own site
<a href="https://agentmods.dev/skills/piyushptiwari1/mcpkernel/research-and-improve"><img src="https://agentmods.dev/badge/skills/piyushptiwari1/mcpkernel/research-and-improve/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.

agentmods 80×15 button for research-and-improve

Your own site · 80×15
<a href="https://agentmods.dev/skills/piyushptiwari1/mcpkernel/research-and-improve"><img src="https://agentmods.dev/badge/skills/piyushptiwari1/mcpkernel/research-and-improve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 441 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found 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 5.1 $0.00048 $0.00441
Opus 5 $0.00024 $0.00220
Sonnet 5 $0.00010 $0.00088
Haiku 4.5 $0.00005 $0.00044

Measured 10d ago against content hash 0b5de00c821a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

research-and-improve 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 10d 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.

.github/skills/research-and-improve/SKILL.md · 54 lines

What it actually says

Research and Improve Workflow

When to Use

  • Discovering and implementing latest security techniques
  • Optimizing performance based on current best practices
  • Upgrading protocol support (MCP, A2A)
  • Adding new sandboxing or taint tracking capabilities

Procedure

Step 1: Research

  1. Search for latest MCP protocol specification updates
  2. Research current security approaches for:
    • Taint analysis and information flow control
    • Container sandboxing advancements
    • eBPF security monitoring
    • Policy engine improvements
  3. Look for Python async optimization techniques
  4. Check for new OWASP ASI guidelines

Step 2: Evaluate Applicability

  1. Read current MCPKernel implementation in src/mcpkernel/
  2. Compare with researched techniques
  3. Identify improvements that:
    • Fit MCPKernel's async Python architecture
    • Don't break existing APIs
    • Have measurable impact

Step 3: Implement

  1. Create a feature branch: feature/<improvement-name>
  2. Write tests first for the new behavior
  3. Implement the improvement with minimal changes
  4. Run full test suite: python -m pytest tests/ -v --tb=short

Step 4: Document

  1. Update docs/USAGE.md if usage changes
  2. Update CHANGELOG.md with the improvement
  3. Update README.md if it's a notable feature

Step 5: Report

Return research findings, what was implemented, and validation results.

References

  • MCPKernel architecture: src/mcpkernel/
  • Configuration: src/mcpkernel/config.py
  • Proxy layer: src/mcpkernel/proxy/
  • Policy engine: src/mcpkernel/policy/
  • Taint tracking: src/mcpkernel/taint/
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. 10d ago First seen · 54 lines · 48 tokens per session scan A 0b5de00c821a

Subscribe to this mod's changes

research-and-improve is a skill published in the GitHub repository piyushptiwari1/mcpkernel (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 48 tokens to every session and 441 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 2026-08-31.

Related

Other skills, from other repositories

skill-inspector

Review AI agent skills before installation using NVIDIA SkillSpector and source-aware semantic review. Use when asked whether a skill or downloaded skill folder is safe, trustworthy, installable, over-permissioned, or malicious.

NVIDIA/SkillSpector · 47 tokens

integrate-arcjet-guard-claude-agent-sdk

Integrate Arcjet security into a Claude Agent SDK agent using @arcjet/guard — wrap tool() handlers, screen inbound prompts with UserPromptSubmit, and deny unwrapped built-in/MCP tools with PreToolUse. Use when asked to add Arcjet to a Claude Agent SDK or Claude Code agent, rate limit its tools, screen inbound…

arcjet/arcjet-js · 92 tokens

integrate-arcjet-guard-genkit

Integrate Arcjet security into a Genkit JS agent using @arcjet/guard — wrap ai.defineTool, put guardMiddleware on generate({ use }) for unwrapped / MCP / filesystem tools, and read a caller-owned id from generate({ context }). Use when asked to add Arcjet to genkit, rate limit its tools, screen inbound messages, or…

arcjet/arcjet-js · 89 tokens

integrate-arcjet-guard-langchain

Integrate Arcjet security into a LangChain JS createAgent using @arcjet/guard — wrap tool() / StructuredTool, put guardMiddleware on createAgent({ middleware }) for MCP / unwrapped tools, and read configurable.threadid for correlation. Use when asked to add Arcjet to langchain createAgent, rate limit its tools, screen…

arcjet/arcjet-js · 101 tokens

integrate-arcjet-guard-langgraph

Integrate Arcjet security into a LangGraph Graph API agent using @arcjet/guard — wrap tool() / StructuredTool, wrap ToolNode for unwrapped MCP tools, and read threadid for correlation. Use when asked to add Arcjet to a LangGraph StateGraph / ToolNode agent, rate limit its tools, screen inbound messages, or block…

arcjet/arcjet-js · 87 tokens

integrate-arcjet-guard-mastra

Integrate Arcjet security into a Mastra agent using @arcjet/guard — wrap createTool execute, screen input/output with a Processor tripwire, and gate unwrapped MCP/workspace tools with hooks. Use when asked to add Arcjet to a Mastra agent, rate limit its tools, screen inbound messages, or block prompt injection / PII.

arcjet/arcjet-js · 82 tokens