Borrowing it
Nothing to install: this file belongs to 0xtrou/gumpbox-extensions. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/0xtrou/gumpbox-extensions/main/AGENTS.mdgit clone --depth 1 https://github.com/0xtrou/gumpbox-extensionsWrote 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/0xtrou/gumpbox-extensions/agents-md)<a href="https://agentmods.dev/instructions/0xtrou/gumpbox-extensions/agents-md"><img src="https://agentmods.dev/badge/instructions/0xtrou/gumpbox-extensions/agents-md/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.
<a href="https://agentmods.dev/instructions/0xtrou/gumpbox-extensions/agents-md"><img src="https://agentmods.dev/badge/instructions/0xtrou/gumpbox-extensions/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.05209 | $0.05209 |
| Opus 5.5 | $0.02084 | $0.02084 |
| Sonnet 5.5 | $0.01042 | $0.01042 |
| Haiku 4.5 | $0.00521 | $0.00521 |
Grade D, and why
gumpbox-extensions AGENTS.md scanned grade D with 3 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 2mo 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 agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- **Never stored in** env vars, client MCP config files, or source. Client configs (`~/.claude.json`, `~/.codex/config.toml`, `~/.gemini/settings.json`) reference only the `gumpbox proxy` binary path + `["proxy"]` args. Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
cd / && rm -rf $TESTDIR Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
| VSCode / Cursor / Windsurf / Continue | `.vsix` extension | Bundled proxy spawn via `child_process`. Configured via extension's `Gumpbox: Set Session URL` command. | How it starts
The opening of the file, as written. The whole thing — 323 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gumpbox-extensions
Open-source MCP client plugins for the gumpbox app.
Bridges AI coding assistants (Claude Code, Codex, Cursor, Windsurf, Continue, VSCode, Gemini) to gumpbox's existing HTTP MCP server via a stdio proxy. One npm package (@gumpbox/cli), one bin (gumpbox), MIT-licensed.
Tech Stack
| Layer | Technology |
|---|---|
| Language | TypeScript 5.6+ |
| Runtime | Node.js 20+ |
| Package manager | pnpm 9.12.0 workspaces |
| Bundler | esbuild (bin), tsc (library dist) |
| Release | Changesets |
| Target | macOS / Linux / Windows (cross-platform, no native modules) |
| Transport | HTTP loopback to gumpbox's 127.0.0.1:<port>/global/mcp/<token> |
| VSCode extension | esbuild-bundled CJS, VSCode 1.95+ |
Project Structure
gumpbox-extensions/
├── packages/
│ └── cli/ # @gumpbox/cli — the single npm package
│ ├── src/
│ │ ├── bin.ts # bin entry, subcommand dispatch
│ │ ├── proxy.ts # stdio JSON-RPC loop (runStdioProxy)
│ │ ├── client.ts # MCPClient — HTTP MCP client
│ │ ├── session.ts # session.json read/write, URL validation
│ │ ├── skills.ts # 6 bundled starter skills (inlined)
│ │ ├── types.ts # JSON-RPC + MCP types
│ │ ├── errors.ts # GumpboxError class + codes
│ │ └── index.ts # library re-exports
│ ├── bin/gumpbox.js # esbuild-bundled single file
│ ├── dist/ # tsc output (library)
│ ├── esbuild.config.mjs
│ ├── tsconfig.json
│ └── package.json
│
├── clients/
│ ├── vscode/ # .vsix — covers VSCode/Cursor/Windsurf/Continue
│ │ ├── src/
│ │ │ ├── extension.ts # activation, commands, status bar
│ │ │ ├── mcpServer.ts # spawns gumpbox proxy as child process
│ │ │ ├── sessionConfig.ts # syncs secret storage ↔ session.json
│ │ │ └── panels/
│ │ │ ├── SkillsPanel.ts # webview: live skills directory
│ │ │ ├── ReadmePanel.ts # webview: readme.get render
│ │ │ ├── ActivityPanel.ts # webview: activities.list timeline
│ │ │ └── panelUtils.ts
│ │ ├── esbuild.config.mjs
│ │ ├── package.json # VSCode extension manifest
│ │ └── tsconfig.json
│ ├── claude-code/ # installer + mcp-config template
│ │ ├── install.sh # POSIX installer
│ │ ├── install.ps1 # Windows installer
│ │ ├── mcp-config.template.json
│ │ └── package.json # name stub for changesets
│ ├── codex/ # installer + config.toml template
│ └── gemini/ # installer + settings.json template
│
├── .changeset/ # Changesets config
├── .github/workflows/ # ci.yml, release.yml, publish-vscode.yml
├── docs/
│ ├── architecture.md
│ ├── adding-a-client.md
│ ├── releasing.md
│ └── manual-testing.md
├── package.json # root workspace
├── pnpm-workspace.yaml
├── tsconfig.base.json
├── LICENSE # MIT
└── README.md
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.
- 2mo ago First seen · 323 lines · 5,209 tokens per session scan D 1da7d265c5d6
gumpbox-extensions AGENTS.md is an instructions file published in the GitHub repository 0xtrou/gumpbox-extensions (1 stars, last pushed 3mo ago), licensed MIT. It adds 5,209 tokens to every session, about $0.0208 per session on Opus 5.5. A static security scan graded it D with 3 findings (reads agent configuration directories, recursive force delete, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
gumpbox-extensions AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| gumpbox-extensions AGENTS.md0xtrou/gumpbox-extensions | Instructions file | 1 | 3mo ago | MIT | D | 5,209 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |