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/midnightmarathon/securetools/agents-mdgit clone --depth 1 https://github.com/MidnightMarathon/securetoolsWhat 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 | $0.02499 | $0.02499 |
| Opus 5 | $0.01249 | $0.01249 |
| Sonnet 5 | $0.00500 | $0.00500 |
| Haiku 4.5 | $0.00250 | $0.00250 |
Grade A, and why
securetools 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 yesterday.
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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions for SecureTools
This file is for AI coding agents (OpenClaw, Copilot, Codex, Devin, SWE-Agent, etc.). It describes the project rules, conventions, and workflows you must follow when contributing.
Project Summary
SecureTools is a collection of client-side browser tools at securegenerators.com. Every tool runs entirely in the browser with zero backend, zero tracking, and zero data collection. The codebase is vanilla HTML, CSS, and JavaScript — no frameworks, no build step, no node_modules.
Repository: MidnightMarathon/securetools
Hard Rules (will fail CI or be rejected if violated)
- No frameworks. No React, Vue, Svelte, Angular, jQuery, Tailwind, or any CSS/JS framework.
- No build step. No Webpack, Vite, Rollup, esbuild, or bundlers. No
package.jsonin the repo. - No server-side code. No backend, no API calls with user input, no form submissions to a server.
- No tracking. No analytics, no cookies, no fingerprinting, no telemetry of any kind.
- No inline JavaScript in HTML. All JS goes in a separate
.jsfile loaded withdefer. Noonclick,oninput, or<script>blocks in HTML. - CDN scripts require SRI. Every
<script src="https://...">must haveintegrity="sha384-..."andcrossorigin="anonymous". Generate hashes at srihash.org. - Shared CSS only. All tools link
/assets/styles.css. Tool-specific overrides go in a small<style>block or a local.cssfile — never duplicate the shared styles.
File Structure
/
├── index.html ← Home page (tool grid)
├── about.html ← About page
├── assets/
│ └── styles.css ← Shared stylesheet (all tools use this)
├── tool-template/ ← Starting point for new tools (copy this)
│ ├── index.html
│ ├── script.js
│ └── README.md
├── <tool-name>/ ← Each tool is a folder at the repo root
│ ├── index.html
│ ├── script.js
│ └── README.md ← Optional but encouraged
├── .github/
│ ├── CODEOWNERS
│ ├── workflows/ci.yml ← CI: HTML validation, SRI check, link check
│ ├── ISSUE_TEMPLATE/ ← Bug report and new tool proposal templates
│ └── PULL_REQUEST_TEMPLATE.md
├── CONTRIBUTING.md ← Full contributor guide
├── AGENTS.md ← This file
└── 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.
- yesterday First seen · 200 lines · 2,499 tokens per session scan A 82202df5d3e6
securetools AGENTS.md is an instructions file published in the GitHub repository MidnightMarathon/securetools (2 stars, last pushed 3mo ago), licensed MIT. It adds 2,499 tokens to every session, about $0.0125 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
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.
buildNext
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
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
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.