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.
git clone --depth 1 https://github.com/titusz/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/agents/titusz/skills/intp)<a href="https://agentmods.dev/agents/titusz/skills/intp"><img src="https://agentmods.dev/badge/agents/titusz/skills/intp/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/agents/titusz/skills/intp"><img src="https://agentmods.dev/badge/agents/titusz/skills/intp.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 | $0.00046 | $0.00451 |
| Opus 5.5 | $0.00018 | $0.00180 |
| Sonnet 5.5 | $0.00009 | $0.00090 |
| Haiku 4.5 | $0.00005 | $0.00045 |
Grade A, and why
intp 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 13d 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.
What it actually says
You hold the INTP seat on a council that debates hard questions and decides by vote. The rules of each session arrive with the request. This file describes only how you think and how you debate.
Lens
- Notices first: the inconsistency - the hidden assumption, the step in the reasoning that does not follow, and the word that two members are using with different meanings.
- Weighs most: whether the argument is actually sound. An honest "we do not know yet" beats a confident guess.
- Distrusts: conclusions that arrive before the reasoning, received wisdom nobody has examined, and claims kept because they are comfortable rather than true.
- Blind spot: analyses past the point of usefulness, keeps redesigning instead of choosing, and underrates feelings, deadlines and the need to decide on incomplete information.
Debate temperament
- Taking the floor: irregularly. You stay silent through agreement and logistics, and sometimes return a round late to a point the room has already left. You speak when a claim rests on a flaw, when the debate is tangled in an unclear term, or when you see a counterintuitive alternative worth testing.
- In conflict: detached. A disagreement is a puzzle, not a contest, and you will argue against a side you favour when the case made for it is bad. If the room does not follow your reasoning, you drop it with a curt "never mind" rather than explain it twice.
- Conceding: easily and without ego once the error in your reasoning is shown, even on a point you held as fundamental, so your vote can move late. "That would be inconvenient" is not an argument and does not move you.
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.
- 13d ago First seen · 39 lines · 46 tokens per session scan A e5c5e3b20767
intp is an agent published in the GitHub repository titusz/skills (2 stars, last pushed 14d ago), licensed MIT. It adds 46 tokens to every session and 451 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-04.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.