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 skills add hexacron/claude-transformatron-9000 --skill maltego-trx-migration-plannergit clone --depth 1 https://github.com/hexacron/claude-transformatron-9000Wrote 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/skills/hexacron/claude-transformatron-9000/maltego-trx-migration-planner)<a href="https://agentmods.dev/skills/hexacron/claude-transformatron-9000/maltego-trx-migration-planner"><img src="https://agentmods.dev/badge/skills/hexacron/claude-transformatron-9000/maltego-trx-migration-planner/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/skills/hexacron/claude-transformatron-9000/maltego-trx-migration-planner"><img src="https://agentmods.dev/badge/skills/hexacron/claude-transformatron-9000/maltego-trx-migration-planner.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 | $0.00042 | $0.02344 |
| Opus 5 | $0.00021 | $0.01172 |
| Sonnet 5 | $0.00008 | $0.00469 |
| Haiku 4.5 | $0.00004 | $0.00234 |
Grade A, and why
maltego-trx-migration-planner 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 10d 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maltego TRX Migration Planner Skill
Purpose
Inspect a TRX-based transform project read-only and produce a structured migration plan that another agent (the implementer) can execute. Do NOT make code changes during planning.
Golden Rule
Produce a plan document BEFORE any broad code changes. The planner's output is a migration plan — not code.
Default Migration Contract
When the user asks for a TRX-to-SDK migration and does not provide a more specific contract, infer this default:
- Preserve externally visible transform behavior.
- Preserve transform IDs/names unless incompatible with SDK naming.
- Preserve input/output entity types and key properties.
- Preserve settings semantics, including auth, optionality, popup/global behavior, and runtime names.
- Preserve API/client behavior, including request parameters, response parsing, pagination, retries, shared/singleton clients, and no-result handling.
- Preserve user-visible messages and error behavior where the SDK has an equivalent.
- Use source behavior evidence to decide what must be kept, but rewrite transform authoring to SDK-native APIs.
- Do not preserve TRX registry/wrapper/discovery artifacts unless explicitly requested.
If the source behavior is ambiguous, record a concrete assumption in the plan and continue with the safest SDK-native migration. Do not ask the user to provide obvious defaults that can be inferred from source.
Step-by-Step: Plan a TRX Migration
1. Read-Only Project Inspection
Start with file discovery — no edits:
find . -name "*.py" | sort
ls -la
cat pyproject.toml 2>/dev/null || cat setup.py 2>/dev/null || cat requirements.txt 2>/dev/null
Identify:
- Project structure (single file vs. package)
- TRX version in use (
from maltego_trx.*orfrom extensions.*) - Number of transform classes
- Public transform IDs, display names, input entities, output entities, and settings from registries, decorators, CSV/config files, and transform classes
- API/client modules used by transforms, including shared clients and request construction helpers
- No-result, partial-result, exception, and user-message behavior
- If the source resembles the public
MaltegoTech/maltego-trx-examplesproject, loadreferences/known-trx-examples.mdbefore planning so you can compare TRX patterns such asregister_transform_function,MaltegoTransform().returnOutput(),request.Slider, sidecar CSV lookups, and entity aliases likemaltego_trx.entities.IPAddress.
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/known-trx-examples.md 4.0 KB
- references/standard-entity-selection.md 4.2 KB
- references/trx-risk-taxonomy.md 6.3 KB
- references/trx-to-sdk-mapping.md 8.6 KB
- scripts/README.md 2.0 KB
- scripts/std_entity_lookup.py 4.6 KB runs code
- scripts/trx_contract.py 11 KB runs code
- scripts/trx_inventory.py 11 KB runs code
- scripts/trx_migration_report.py 9.9 KB runs code
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.
- 10d ago First seen · 231 lines · 42 tokens per session scan A 6d1a1c3bd8e3
maltego-trx-migration-planner is a skill published in the GitHub repository hexacron/claude-transformatron-9000 (0 stars, last pushed 23d ago), licensed MIT. It adds 42 tokens to every session and 2,344 once invoked, about $0.0002 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…