Pydantic Deep Agents is a self-hosted terminal AI assistant and Python framework for building coding, research, and other AI agents. It gives agents tools such as file access, shell commands, planning, memory, sub-agents, sandboxed execution, and MCP connections, and supports different models.
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 vstorm-co/pydantic-deepagents --skill report-writinggit clone --depth 1 https://github.com/vstorm-co/pydantic-deepagentsWrote 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/vstorm-co/pydantic-deepagents/report-writing)<a href="https://agentmods.dev/skills/vstorm-co/pydantic-deepagents/report-writing"><img src="https://agentmods.dev/badge/skills/vstorm-co/pydantic-deepagents/report-writing/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/vstorm-co/pydantic-deepagents/report-writing"><img src="https://agentmods.dev/badge/skills/vstorm-co/pydantic-deepagents/report-writing.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 | $0.00014 | $0.00433 |
| Opus 5 | $0.00007 | $0.00217 |
| Sonnet 5 | $0.00003 | $0.00087 |
| Haiku 4.5 | $0.00001 | $0.00043 |
Grade A, and why
report-writing 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.
What it actually says
Report Writing Guide
Report Structure
1. Title
- Descriptive and specific
- Include the scope or time frame if relevant
- Example: "Advances in Protein Folding Since AlphaFold 3 (2024-2025)"
2. Executive Summary
- 2-3 paragraphs summarizing key findings
- Written last, after the full report is complete
- Should stand alone — a reader should understand the main conclusions
3. Body Sections
- Organize logically (chronological, thematic, or comparative)
- Each section should address one sub-topic
- Use inline citations [1][2] for every factual claim
- Include data, statistics, and direct quotes where appropriate
4. Conclusions
- Synthesize findings across all sections
- Highlight key takeaways and implications
- Note limitations of the research
- Suggest areas for further investigation
5. References
- Number references in order of first appearance
- Format:
[N] Author/Organization, "Title", URL, Accessed: YYYY-MM-DD
Writing Style
Clarity
- Use clear, direct language
- Define technical terms on first use
- Prefer active voice over passive
- Keep paragraphs focused on one idea
Objectivity
- Present evidence before conclusions
- Acknowledge counter-arguments
- Use hedging language for uncertain claims ("suggests", "indicates", "appears to")
- Distinguish between facts and interpretation
Citation Practices
- Cite every factual claim, statistic, and quote
- Use inline citations [N] immediately after the claim
- Multiple citations for well-supported claims: [1][3][7]
- Never present information without attribution
Formatting Tips
- Use headers (##, ###) to create clear hierarchy
- Use bullet points for lists of findings
- Use tables for comparative data
- Use blockquotes for direct quotes from sources
- Bold key terms and important findings
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 · 64 lines · 14 tokens per session scan A e520b9284707
report-writing is a skill published in the GitHub repository vstorm-co/pydantic-deepagents (1,059 stars, last pushed 18d ago), licensed MIT. It adds 14 tokens to every session and 433 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
pydantic-ai
Build production-ready AI agents with PydanticAI — type-safe tool use, structured outputs, dependency injection, and multi-model support.
hive.slack-notifications-setup
Set up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive Sentinel" Slack app from a JSON manifest, install it, capture the bot + app tokens, create/select the channel via the Slack API, and turn Sentinel on so the colony can ping the user on Slack and accept…
hive.pdf
Read, write, merge, split, rotate, watermark, encrypt, and OCR PDF files using Python (pypdf, pdfplumber, reportlab, pypdfium2) and command-line tools (poppler-utils, qpdf). Use when the user asks to extract text/tables/images from a PDF, create or modify a PDF, combine or split PDFs, OCR a scanned PDF…
hive.chart-creation-foundations
Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
hive.note-taking
Maintain a free-form scratchpad of decisions, extracted values, and open questions so context pruning doesn't lose anything you still need.