claude-transformatron-9000 AGENTS.md

claude-transformatron-9000 AGENTS.md is an instructions file for Codex, OpenCode from hexacron/claude-transformatron-9000. It costs 1,357 tokens per session, scanned A, original, MIT.

Repository instructions for coding agents working on claude-transformatron-9000. The project is a local control system and command-line tool for starting and running one Maltego transform server.

In plain words
What is it for?
They help agents operate the server, follow the transform-authoring rules, and use the documented development loop and verification steps.
Why use it?
They explain the project's purpose, required preparation before editing transforms, and the checks agents should follow while working.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/hexacron/claude-transformatron-9000/agents-md
Clone the repo
git clone --depth 1 https://github.com/hexacron/claude-transformatron-9000

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 claude-transformatron-9000 AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/hexacron/claude-transformatron-9000/agents-md.svg)](https://agentmods.dev/instructions/hexacron/claude-transformatron-9000/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/hexacron/claude-transformatron-9000/agents-md"><img src="https://agentmods.dev/badge/instructions/hexacron/claude-transformatron-9000/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,357 This file is loaded in full into every session.
When invoked 1,357 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01357 $0.01357
Opus 5 $0.00678 $0.00678
Sonnet 5 $0.00271 $0.00271
Haiku 4.5 $0.00136 $0.00136

Measured 4d ago against content hash c5751b1b2cbe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

claude-transformatron-9000 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 4d 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.

AGENTS.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent guide

Instructions for coding agents working in this repository. This is the canonical file — CLAUDE.md points here. It follows the AGENTS.md convention, which Codex, Gemini CLI, and other agents read directly.

Humans: README.md is the friendlier entry point, but nothing here is agent-only.

What this project is

An MCP control plane and CLI for a single local Maltego v3 transform server. It handles the server lifecycle and transform execution. It does not help you write transform code.

Before writing a transform

Read docs/transform-authoring.md first. It documents two SDK behaviours that fail silently — code that looks right, runs green, and produces nothing. The vendored SDK guidance in server/.agents/skills/ teaches one of them.

Claude Code loads the same checklist automatically from .claude/skills/maltego-transform-author/SKILL.md. That file is a thin pointer to docs/transform-authoring.md, not a second copy, so nothing here is Claude-only. Working through this file instead gets you the same result.

The short version, in the order these bite:

  1. Return a list, never a MaltegoGraph — a returned graph is silently discarded.
  2. Annotate both the first parameter and the return type; a bare -> list publishes output NONE.
  3. Import the module in server/project.py, or it never registers.
  4. Check the entity count. A success state is not proof of anything.
  5. Credentials belong in TransformSetting(auth=True, is_global=True), never hardcoded.
  6. Validate input_entity.value before putting it in a URL or a subprocess call.

The loop

  1. Add or edit a module under server/transforms/.
  2. Import it in server/project.py — the server only registers what project.py imports.
  3. Restart the server.
  4. Confirm it registered, then run it.

Driving the server

Two interchangeable front ends over the same transformatron.operations module. Use whichever your tool supports.

CLI — works anywhere you can run a command:

Read the full file on GitHub · 133 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. 4d ago First seen · 133 lines · 1,357 tokens per session scan A c5751b1b2cbe

Subscribe to this mod's changes

claude-transformatron-9000 AGENTS.md is an instructions file published in the GitHub repository hexacron/claude-transformatron-9000 (0 stars, last pushed 18d ago), licensed MIT. It adds 1,357 tokens to every session, about $0.0068 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

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 · 5,182 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

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

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

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

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