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/aberemia24/code-executor-mcp/agents-mdgit clone --depth 1 https://github.com/aberemia24/code-executor-MCPWhat 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 | $0.00749 | $0.00749 |
| Opus 5 | $0.00375 | $0.00375 |
| Sonnet 5 | $0.00150 | $0.00150 |
| Haiku 4.5 | $0.00075 | $0.00075 |
Grade B, and why
code-executor-MCP AGENTS.md scanned grade B with 1 finding 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.
Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
Configuration is managed through env vars parsed in `src/config.ts` plus optional overrides in `config/.mcp.json`; keep secrets out of version control. Update `SECURITY.md`, AppArmor/Seccomp profiles, and rate-limit defa How it starts
The opening of the file, as written. The whole thing — 25 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
Runtime code sits in src/, where index.ts wires client pools, sandbox executors, rate limiters, and validators defined under schemas/, interfaces/, and types/; dist/ holds the compiled CLI. Reference docs, release notes, and deployment guides live in docs/, specs/, RELEASE*.md, and WORKTREE-GUIDE.md. Sample agent flows are in examples/, while operational artifacts (apparmor-profile, seccomp-profile.json, config/.mcp.json, logs/, audit.log) capture security posture. Tests live mostly in tests/ (helpers, docker checks, integrations) with a few targeted .test.ts files colocated in src/.
Build, Test, and Development Commands
npm install– install Node 22+ dependencies.npm run dev– watch/compile TypeScript while editing.npm run build && npm start– emitdist/and launch the MCP server locally.npm run generate-wrappers– regenerate tool wrappers after schema changes.npm run typecheckandnpm run lint/lint:fix– enforce strict typing and ESLint rules.npm test,npm run test:watch, andnpm run test:coverage– execute the Vitest suite and capture V8 coverage.
Coding Style & Naming Conventions
TypeScript targets ES2022 with strict + NodeNext modules; keep 2-space indentation, single quotes, kebab-case filenames, camelCase functions, and PascalCase types. Avoid any, prefer unknown plus guards or Zod schemas, and state return types on exported APIs. Keep async code await-driven, reuse helpers from src/utils.ts, and let ESLint (eslint.config.mjs) enforce import order, unused symbols, and import type patterns.
Testing Guidelines
Vitest powers both unit and integration suites. Place behavior-heavy tests in tests/ (lean on tests/helpers for fixtures and tests/integration for MCP-client exercises) and keep fast schema checks next to the source. Name specs should_<behavior>_when_<condition>. Run npm test before commits and npm run test:coverage when touching core flows; expect ≥90% coverage. Execute test-security.sh or test-docker-security.sh after sandbox or container 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.
- 2d ago First seen · 25 lines · 749 tokens per session scan B 1d191db3a5e6
code-executor-MCP AGENTS.md is an instructions file published in the GitHub repository aberemia24/code-executor-MCP (130 stars, last pushed 9mo ago), licensed MIT. It adds 749 tokens to every session, about $0.0037 per session on Opus 5. A static security scan graded it B with 1 finding (reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
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.
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).
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.
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).
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.
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.