Pydantic AI is a typed Python SDK for building AI agents that can use different language models and interfaces, including voice, image generation, and embeddings. Developers use it for applications ranging from structured data extraction to long-running multi-agent work. The catalogue entries provide workflows and configuration for its coding-agent and harness features.
Borrowing it
Nothing to install: this file belongs to pydantic/pydantic-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/pydantic/pydantic-ai/main/.agents/skills/i-have-adhd/SKILL.mdgit clone --depth 1 https://github.com/pydantic/pydantic-aiWrote 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/pydantic/pydantic-ai/i-have-adhd)<a href="https://agentmods.dev/skills/pydantic/pydantic-ai/i-have-adhd"><img src="https://agentmods.dev/badge/skills/pydantic/pydantic-ai/i-have-adhd/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/pydantic/pydantic-ai/i-have-adhd"><img src="https://agentmods.dev/badge/skills/pydantic/pydantic-ai/i-have-adhd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00107 | $0.01355 |
| Opus 5 | $0.00053 | $0.00678 |
| Sonnet 5 | $0.00021 | $0.00271 |
| Haiku 4.5 | $0.00011 | $0.00136 |
Grade A, and why
i-have-adhd 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 12d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
i-have-adhd
The user has ADHD and reads the agent's output; the agent does the work. Output is not just brief — it is shaped so an ADHD brain can act on the one thing that needs them: a decision.
What ADHD changes about reading
Four facts drive every rule below:
- Working memory is small. Anything off-screen is gone. Never say "keep in mind X" or "remember we decided Y" — restate it.
- A buried ask is a missed ask. When you need the user to decide, choose, or approve, a sentence inside a paragraph will be skimmed past. The ask must be un-missable.
- Time estimates feel uniform. "Some work" and "a few hours" register the same. Ballpark in concrete units.
- Dopamine is scarce. Visible progress registers; buried wins don't. Lead with what now works.
Rules
1. Lead with the result or the decision
The first line is the outcome, the answer, or the decision you need — never the runway. Not "Let me look at this," not a plan of what you're about to do.
Bad: "Let's think about this. Your auth flow has a few moving pieces..." Good: "Login works with magic links now, server is running, here's the link for you to verify ..."
If the answer is a command, path, or snippet, it goes first. Prose after, if at all.
2. Every ask is a structured question
When you need the user to decide, choose, or approve, or even just be aware of something very important ("confirm I read"), raise it with your harness's structured question tool (AskUserQuestion in Claude Code) — never as a question embedded in prose. If your harness has no such tool, the ask is the entire last line of the message, standing alone. One decision inside a paragraph is a decision missed.
Applies to real ambiguity too: don't guess and rewrite later. One structured question beats a wrong assumption.
3. Suppress tangents; a second issue is a second ask
Finish the thing at hand. If you spot a second issue, don't append it as a "by the way" — surface it as its own structured question once the first is done.
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.
- 12d ago First seen · 97 lines · 107 tokens per session scan A 8bfa872b719e
i-have-adhd is a skill published in the GitHub repository pydantic/pydantic-ai (19,869 stars, last pushed today), licensed MIT. It adds 107 tokens to every session and 1,355 once invoked, about $0.0005 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
mem0-status
Diagnoses mem0 connectivity, API key validity, and memory read/write functionality. Use when memory operations fail, searches return empty, addmemory errors occur, or to verify the plugin is working correctly.
reproduce-bug
Reproduce a reported bug in googleapis/mcp-toolbox and decide whether it is real, delivering an evidence-backed verdict: confirmed, already fixed, misconfiguration, client-side, works as intended, not reproducible, or blocked. Use whenever a maintainer asks you to reproduce, verify, confirm, or investigate a bug…
fix-failing-tests
Diagnose a failing test in the googleapis/mcp-toolbox repo and land a fix by reasoning from the actual error: read the failure, reproduce it, shrink it until the cause is forced into the open, then fix the cause. Use this whenever a test or CI job is red, a build breaks after a change, many packages fail at once, or a…
triage-issues
Triage GitHub issues in the googleapis/mcp-toolbox repo: propose the correct labels (type / priority / product / status), check for duplicates, verify a bug has enough info to act on, and draft a triage comment. Use whenever a maintainer asks you to triage, label, categorize, prioritize, or "look at" an issue (or a…
python-code-quality
Code quality checks, linting, formatting, and type checking commands for the Agent Framework Python codebase. Use this when running checks, fixing lint errors, or troubleshooting CI failures.
credit-note-fixer
Fix the tiny credit-note formatting bug and rerun the exact targeted test command.