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/aself101/mcp-secure-server/agents-mdgit clone --depth 1 https://github.com/aself101/mcp-secure-serverWhat 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 | $0.00697 | $0.00697 |
| Opus 5 | $0.00349 | $0.00349 |
| Sonnet 5 | $0.00139 | $0.00139 |
| Haiku 4.5 | $0.00070 | $0.00070 |
Grade A, and why
mcp-secure-server 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 2d 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 — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
Source lives in src/, where index.ts re-exports the secure server, security/ contains the layered middleware and transports, and types/ stores shared definitions. Tests mirror this layout under test/unit, test/integration, and test/performance. Docs sit in docs/, examples in cookbook/, and builds in dist/ (never edit generated files).
Build, Test, and Development Commands
npm run build– runstscand refreshesdist/.npm test– executes the entire Vitest suite; required before any PR.npm run test:unit|test:integration|test:performance– scope runs to the feature you are touching.npm run test:watch/npm run test:coverage– watch locally and regenerate the ≥86% coverage report before releases.npm run minimal-server– bootscookbook/minimal-server/minimal-test-server.tsfor manual probing.npm run lint– enforces the shared ESLint configuration acrosssrc/.
Coding Style & Naming Conventions
Write TypeScript (ES modules, Node ≥18) with 2-space indentation and relative imports. Classes/interfaces are PascalCase, functions/variables camelCase, constants UPPER_SNAKE_CASE, and filenames should state the layer they implement (layer3-behavior.ts, secure-transport.ts). Keep modules ≈300 LOC per docs/AI-preferences.md, reuse utilities, and rely on npm run lint to enforce ESLint + @typescript-eslint.
Layer Implementation Notes
Validation layers extend ValidationLayerBase, implement validate(message, context) with the standard { passed, allowed, severity, reason, violationType } shape, must flow through ValidationPipeline, sanitize errors with ErrorSanitizer, source attack patterns from src/security/layers/layer-utils/content/dangerous-patterns.ts, and expose options via SecureMcpServer.
Testing Guidelines
Vitest drives every suite; keep specs *.test.ts/*.test.js inside the matching test/<suite>/ folder so targeted runs stay fast. Validator or limit updates must ship with regression tests plus payload fixtures in cookbook/test-data/. Maintain ≥85% coverage via npm run test:coverage, note gaps in the PR, and cite npm run minimal-server when verifying transports.
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.
- 2d ago First seen · 28 lines · 697 tokens per session scan A 322c60426ad0
mcp-secure-server AGENTS.md is an instructions file published in the GitHub repository aself101/mcp-secure-server (2 stars, last pushed 9d ago), licensed MIT. It adds 697 tokens to every session, about $0.0035 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
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).
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.