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 environment-discoverygit 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/environment-discovery)<a href="https://agentmods.dev/skills/vstorm-co/pydantic-deepagents/environment-discovery"><img src="https://agentmods.dev/badge/skills/vstorm-co/pydantic-deepagents/environment-discovery/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/environment-discovery"><img src="https://agentmods.dev/badge/skills/vstorm-co/pydantic-deepagents/environment-discovery.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 | $0.00013 | $0.00422 |
| Opus 5 | $0.00006 | $0.00211 |
| Sonnet 5 | $0.00003 | $0.00084 |
| Haiku 4.5 | $0.00001 | $0.00042 |
Grade A, and why
environment-discovery 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.
What it actually says
Environment Discovery
When dropped into an unfamiliar environment, ALWAYS explore before acting.
Step 1: Understand the workspace
ls -la /app/ # or the working directory
find . -type f | head -50
- What files exist? What are their sizes?
- Are there READMEs, Makefiles, config files?
- What languages/frameworks are involved?
Step 2: Inspect data files
Before writing any code that reads data, understand the format:
file <filename>— detect file type (binary, text, encoding)head -20 <file>— first lines of text filesxxd <file> | head -20— hex dump for binary fileswc -l <file>— line count for text filesstat <file>— exact file size in bytespython3 -c "import struct; ..."— parse binary headers
Step 3: Check available tools
which python3 gcc g++ make cmake node npm cargo rustc java go
pip list 2>/dev/null | head -20
- What compilers/interpreters are installed?
- What libraries are available?
- What package managers can you use?
Step 4: Read existing code
If there are existing source files:
- Read them FULLY before modifying
- Understand the build system (Makefile, CMakeLists.txt, pyproject.toml)
- Check for existing tests
Key Principles
- NEVER assume file formats — always inspect first
- NEVER assume tools are installed — always check
- A 500MB file is NOT a "small file" — plan for it
- Binary files need byte-level inspection, not
cat - Spend 30 seconds exploring to save 5 minutes debugging
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 · 59 lines · 13 tokens per session scan A af3f39242613
environment-discovery is a skill published in the GitHub repository vstorm-co/pydantic-deepagents (1,059 stars, last pushed 18d ago), licensed MIT. It adds 13 tokens to every session and 422 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.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.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.note-taking
Maintain a free-form scratchpad of decisions, extracted values, and open questions so context pruning doesn't lose anything you still need.