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 skills/izar/tm_skills/pytmnpx skills add izar/tm_skills --skill pytmgit 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/pytm)<a href="https://agentmods.dev/skills/izar/tm_skills/pytm"><img src="https://agentmods.dev/badge/skills/izar/tm_skills/pytm.svg" alt="Measured on agentmods" 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 | $0.00024 | $0.00944 |
| Opus 5 | $0.00012 | $0.00472 |
| Sonnet 5 | $0.00005 | $0.00189 |
| Haiku 4.5 | $0.00002 | $0.00094 |
Grade A, and why
pytm threat model 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 5d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
This Skill analyzes the code in your directory and uses the PyTM python library to build a representation (model) and a list of possible threats affecting it.
Method
Copy this checklist and track your progress:
PyTM Threat Model creation progress:
- [ ] Analysis
- [ ] Mapping to pytm elements
- [ ] Adding attributes
- [ ] Create pytm script
- [ ] Execute the script
- [ ] Validate the script
- [ ] Try a use case analysis of the project
Step 1: Analysis
Analyze the codebase (either the current directory or project, or some path or project reference given by the user as an argument in the prompt) looking for the basic architectural components of the system: Actors (which are possibly humans interacting with the system), Clients, Servers, Serverless Processes, Datastores, Trust Boundaries (where the identity of the user or process is different on both sides of a dataflow), and, most importantly, Dataflows that carry data from one element of the system to another. Pay special attention to where in the codebase each one of the elements discovered is created or referred for the first time.
Step 2: Mapping to pytm elements Once you have those elements mapped, use the Python pytm library and create a relationship between what you identified and the pytm building blocks: Asset, Lambda, Server, ExternalEntity, Datastore, Actor, Process, SetOfProcesses, Boundary and Dataflow. You are also free to create pytm assumptions in the form of the assumption attribute of the TM, and any security controls you identify should appear as an addition to the controls attribute of the TM. Particular items of data should be represented using the Data class.
Step 3: Adding attributes For attributes of data instances you can identify from the code and documentation of the project, fill the instances attributes. For anything that you are not sure about, or that you cannot find a value but think is important to have, add a comment like "# TODO - find the real value for this attribute". Make sure that the origin of the element that you remember from Step 1 is the value of the appropriate attribute.
What ships with it
1 file 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.
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.
- 5d ago First seen · 62 lines · 24 tokens per session scan A 9e15f31d4acd
pytm threat model is a skill published in the GitHub repository izar/tm_skills (19 stars, last pushed 1mo ago), licensed MIT. It adds 24 tokens to every session and 944 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…