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.
npx agentmods add instructions/piyushptiwari1/mcpkernel/copilot-instructionsgit clone --depth 1 https://github.com/piyushptiwari1/mcpkernelWrote 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/instructions/piyushptiwari1/mcpkernel/copilot-instructions)<a href="https://agentmods.dev/instructions/piyushptiwari1/mcpkernel/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/piyushptiwari1/mcpkernel/copilot-instructions.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 | $0.01344 | $0.01344 |
| Opus 5 | $0.00672 | $0.00672 |
| Sonnet 5 | $0.00269 | $0.00269 |
| Haiku 4.5 | $0.00134 | $0.00134 |
Grade A, and why
mcpkernel copilot-instructions.md 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 3d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCPKernel — Project Context for All Agents
Project Overview
MCPKernel is an open-source Execution Sovereignty Stack — a mandatory, deterministic MCP/A2A gateway that makes every agent tool call provably replayable, taint-safe, and policy-enforced. Licensed under Apache 2.0.
Repository: piyushptiwari1/mcpkernel
Architecture
- 11 packages in
src/mcpkernel/: proxy, sandbox, dee, taint, context, ebpf, policy, audit, observability, cli, agent_manifest - Proxy: AsyncIO MCP/A2A transparent gateway with SSE/stdio transport
- Policy: YAML-based rules engine with OWASP ASI 2026 mappings
- Taint: Multi-mode taint tracking (FULL/LIGHT/OFF) for secrets, PII, user input
- Sandbox: Docker, Firecracker, WASM, Microsandbox backends
- DEE: Deterministic Execution Envelopes — hashed, Sigstore-signed, replayable
- Audit: Tamper-proof append-only logs with SIEM export (CEF, JSONL, CSV)
- Context: Environment snapshots and drift detection
- Observability: OpenTelemetry metrics and Prometheus export
- eBPF: Kernel-level syscall filtering
- Agent Manifest: agent.yaml loader, policy bridge, tool validator, proxy hook
Code Standards
- Python >=3.12 (tested on 3.12 and 3.13, developed on 3.13.12)
- Async-first using
asyncio - Type hints on all public APIs
- Tests in
tests/usingpytestwith async support - All 695 tests must pass before merging to main
- Coverage must be ≥80% (
python -m pytest --cov=mcpkernel) - Lint clean:
ruff check src/ tests/must show zero errors - Format clean:
ruff format --check src/ tests/must pass
Build & Test
# Install (using uv)
uv venv --python 3.13
source .venv/bin/activate
uv pip install -e ".[dev]"
# Run all tests
python -m pytest tests/ -v --tb=short
# Run specific test module
python -m pytest tests/test_proxy.py -v
# Lint + Format
ruff check src/ tests/
ruff format --check src/ tests/
# Type check
mypy src/mcpkernel/
Git Workflow
mainbranch: stable, all tests passingdevelopmentbranch: active work, may have failing tests- Feature branches:
feature/<description>off development - Bug fix branches:
fix/<description>off development - Always run tests before merging to main
- Use conventional commits:
feat:,fix:,docs:,test:,refactor:,chore:
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.
- 3d ago First seen · 103 lines · 1,344 tokens per session scan A 3e1460e90a3b
mcpkernel copilot-instructions.md is an instructions file published in the GitHub repository piyushptiwari1/mcpkernel (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 1,344 tokens to every session, about $0.0067 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.
Other instructions, from other repositories
AgentHound CLAUDE.md
Claude Code instructions for adithyan-ak/AgentHound, covering agenthound maintainer contract, required checks, hard boundaries, core invariants and module registration.
arcjet-js AGENTS.md
Instructions for arcjet/arcjet-js, covering agent guidance, examples live in arcjet/examples and integration work: review before a pr.
prismor CLAUDE.md
Claude Code instructions for PrismorSec/prismor, covering prismor security — claude.md, prismor runtime protection, cloaking (secret prevention) and working in this repo.
AgentHound copilot-instructions.md
Copilot instructions for adithyan-ak/AgentHound: Keep generated examples local to the fixture project.
ave CLAUDE.md
Claude Code instructions for aveproject/ave, covering claude.md — aveproject/ave, project, the critical distinction — read this twice, record schema v1.1.0 and adding a record.
Agent-Security-Regression-Harness AGENTS.md
Instructions for OWASP/Agent-Security-Regression-Harness, covering ai agent guide: owasp agent security regression harness, project overview, architecture, contribution workflow and what needs doing.