MCP-Sentinel: Instructions file for Codex

AGENTS.md

MCP-Sentinel AGENTS.md is an instructions file for Codex, OpenCode from BashaarJavaid/MCP-Sentinel. It costs 3,921 tokens per session, scanned A, original, MIT.

Project instructions for MCP Sentinel, a command-line tool and GitHub Action that checks Model Context Protocol (MCP) servers for security problems before they run. It uses source-code checks and limited runtime checks and reports results in SARIF, a format used by code-scanning tools.

In plain words
What is it for?
Use it when modifying or reviewing the MCP Sentinel codebase. It helps locate components, follow project conventions, run builds and tests, and understand its scanner and GitHub Action.
Why use it?
It gives a coding agent the project's structure, conventions, commands, and safety rules. This reduces guesses, unnecessary changes, and missed checks while working on the repository.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

This is BashaarJavaid/MCP-Sentinel's own configuration. It tells Codex and OpenCode how to work on MCP-Sentinel 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 MCP-Sentinel configures →

Reuse

Borrowing it

Nothing to install: this file belongs to BashaarJavaid/MCP-Sentinel. 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/BashaarJavaid/MCP-Sentinel/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/BashaarJavaid/MCP-Sentinel

Made for: Codex, OpenCode.

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 MCP-Sentinel AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/bashaarjavaid/mcp-sentinel/agents-md.svg)](https://agentmods.dev/instructions/bashaarjavaid/mcp-sentinel/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/bashaarjavaid/mcp-sentinel/agents-md"><img src="https://agentmods.dev/badge/instructions/bashaarjavaid/mcp-sentinel/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,921 This file is loaded in full into every session.
When invoked 3,921 The same file — it is already loaded in full.
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 $0.03921 $0.03921
Opus 5 $0.01961 $0.01961
Sonnet 5 $0.00784 $0.00784
Haiku 4.5 $0.00392 $0.00392

Measured today against content hash f406bd278975, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

MCP-Sentinel AGENTS.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 today.

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.

AGENTS.md · 269 lines

How it starts

The opening of the file, as written. The whole thing — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Project-specific context and instructions for PortunusMCP Sentinel, merged with a set of general behavioral guidelines (sections 1-4 below, adapted from andrej-karpathy-skills/CLAUDE.md) aimed at reducing common LLM coding mistakes: unstated assumptions, speculative complexity, unrelated edits, and vague success criteria.

Tradeoff: these guidelines bias toward caution over speed. For trivial tasks, use judgment.


Project

PortunusMCP Sentinel — a build-time static/dynamic security scanner for MCP (Model Context Protocol) servers, mapped to the OWASP Agentic Top 10, shipped as a CLI tool and a GitHub Action that outputs SARIF.

Sentinel is one of three components of the PortunusMCP family:

  1. PortunusMCP Gateway — runtime zero-trust enforcement gateway (separate repo, out of scope here).
  2. PortunusMCP Sentinel (this repo) — build-time scanner.
  3. PortunusMCP Identity — short-lived credential broker (separate repo, out of scope here).

Sentinel helps maintainers and small teams catch MCP server security regressions before release, with actionable source findings and reproducible evidence for supported runtime checks. It combines static source/manifest analysis and adversarial probes against sandboxed targets. A completed scan is not proof that a server is safe; OWASP mappings classify findings, not coverage of all ten categories. Start with supported Python server maintainers and expand according to measured detection gaps and pilot demand.

The historical build context lives in mcp-sentinel-buildplan.md; active contracts and status live in ARCHITECTURE.md and ROADMAP.md. Read the historical brief first for project context, then use the active documents as authority.

Where things live

  • mcp-sentinel-buildplan.md — historical build brief and original scope. Read this first for context; defer to Architecture and Roadmap for current contracts.
  • README.md — public quickstart, install, supported scope, and usage examples.
  • src/sentinel/static/rules/ — one file per detection rule; each rule is independently testable and tagged with its OWASP Agentic Top 10 category (src/sentinel/owasp_mapping.py holds the canonical rule-id → category map).
  • src/sentinel/dynamic/ — the sandbox launcher (sandbox.py) and adversarial prober (prober.py).
  • src/sentinel/report/sarif.py (SARIF 2.1.0 writer) and console.py (human-readable terminal report).
  • tests/fixtures/vulnerable_server/ and tests/fixtures/clean_server/ — the reference sample servers every rule is tested against.
  • tests/evals/ and artifacts/ — existing review truth sets and retained evidence; Phase 20 adds independent vulnerable/fixed cases and held-out evaluation. Fixture success and code coverage are not detection accuracy.
  • action.yml — the GitHub Action wrapper around the CLI.

Read the full file on GitHub · 269 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. today Changed · +12 lines · +159 tokens per session f406bd278975
  2. yesterday Changed · +102 lines · +1,324 tokens per session 61ab64b9157f
  3. 3d ago Changed · +11 lines · +212 tokens per session fbff9bde6111
  4. 8d ago First seen · 144 lines · 2,226 tokens per session scan A d2ffc301f13c

Subscribe to this mod's changes

MCP-Sentinel AGENTS.md is an instructions file published in the GitHub repository BashaarJavaid/MCP-Sentinel (5 stars, last pushed today), licensed MIT. It adds 3,921 tokens to every session, about $0.0196 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 instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens