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 izar/tm_skills --skill 4qpytmgit clone --depth 1 https://github.com/izar/tm_skillsWrote 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/izar/tm_skills/4qpytm)<a href="https://agentmods.dev/skills/izar/tm_skills/4qpytm"><img src="https://agentmods.dev/badge/skills/izar/tm_skills/4qpytm/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/izar/tm_skills/4qpytm"><img src="https://agentmods.dev/badge/skills/izar/tm_skills/4qpytm.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 | $0.00025 | $0.00936 |
| Opus 5 | $0.00013 | $0.00468 |
| Sonnet 5 | $0.00005 | $0.00187 |
| Haiku 4.5 | $0.00003 | $0.00094 |
Grade A, and why
4 Questions pytm 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 9d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
This Skill helps you create a threat model of a system at its inception, based on the 4 Questions Framework, some Socratic help and pytm.
Method
**Step 0: The framework This skill helps create the base threat model by asking the user leading questions until it considers it has enough information to build a good representation of the system in question and ellicit threats against it. Litmus test: if questions about the system are about to go bellow the level of the individual process, consider maximal depth reached. The maximum resolution should be at the higher level process, not Unix-level processes.
Copy this checklist and track your progress:
PyTM Threat Model based on the 4 Questions Framework creation progress:
- [ ] What are we building?
- [ ] What can go wrong?
- [ ] What can we do about it?
- [ ] Did we do a good job?
Step 1: What are we building? In this step, you will use the Socratic method to understand from the user what is being built. The first question should always be "What are we building?". Analyze the user's answer and continue asking questions until you are satisfied that you can understand what it is that is being built. Your questions should not go beyond the level of elements of a system like Actor, Server, Client, Process, Business Case, Dataflow, Datastore, Data.
Make sure to tell the user at all times that they are free to end the process by saying something "I don't have more answers" or "I don't have any more details" or "Go ahead and continue with what you have". Respect the user's choice.
Once you are satisfied that you have all the information about the system, or the user has informed you that no more questions will be answered, proceeed to use your pytm skill to build a PyTM based representation of the system in question.
Present the user with the dfd.png diagram (open the file with an auxiliary program like xdg-open if you can) and ask if they recognize the thing they are trying to build.
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.
- 9d ago First seen · 60 lines · 25 tokens per session scan A a5452cdb4d5a
4 Questions pytm is a skill published in the GitHub repository izar/tm_skills (19 stars, last pushed 2mo ago), licensed MIT. It adds 25 tokens to every session and 936 once invoked, about $0.0001 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 2026-08-30.
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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…