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 verification-strategygit 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/verification-strategy)<a href="https://agentmods.dev/skills/vstorm-co/pydantic-deepagents/verification-strategy"><img src="https://agentmods.dev/badge/skills/vstorm-co/pydantic-deepagents/verification-strategy/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/verification-strategy"><img src="https://agentmods.dev/badge/skills/vstorm-co/pydantic-deepagents/verification-strategy.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 | $0.00656 |
| Opus 5 | $0.00006 | $0.00328 |
| Sonnet 5 | $0.00003 | $0.00131 |
| Haiku 4.5 | $0.00001 | $0.00066 |
Grade A, and why
verification-strategy 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.
How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verification Strategy
How to verify your work is correct before declaring a task complete.
The Verification Checklist
After implementing a solution, go through ALL of these:
1. Re-read the original task
- Re-read the EXACT wording of the task instruction
- Check every requirement — file paths, names, formats, constraints
- Are there implicit requirements? ("compile with gcc -O3 -lm" means exact flags)
2. Check file outputs
- Do all required files exist at the exact paths specified?
- Are file sizes within any stated limits?
- Is the file format correct? (binary vs text, encoding, line endings)
ls -la /path/to/expected/output
wc -c /path/to/output # byte count
file /path/to/output # format detection
head -5 /path/to/output # content preview
3. Compile and run
- Compile with the EXACT flags specified in the task
- Run with the EXACT command and arguments specified
- Check exit code:
echo $?(should be 0 for success) - Check both stdout AND stderr
4. Validate output
- Compare output against expected format
- Check exact field names, delimiters, number formatting
- If the task specifies output format, match it exactly:
- JSON: valid JSON? correct schema?
- CSV: correct headers? correct delimiter?
- Plain text: correct line endings? trailing newline?
5. Test edge cases
- Empty input (if applicable)
- The specific test inputs mentioned in the task
- Large inputs (if the task involves performance)
6. Check constraints
- Size limits (file size, code length)
- Time limits (does it finish in reasonable time?)
- Memory limits (does it stay within bounds?)
- No external dependencies that aren't available
Reading Test Scripts
If you can find the test script, READ IT:
- What exact assertions does it make?
- What inputs does it use?
- What output format does it expect?
- What timeouts are set?
Tests often check things you didn't expect:
- Exact string matching (whitespace matters!)
- Specific numeric precision
- File permissions
- Process exit codes
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 · 90 lines · 13 tokens per session scan A b1b3af437396
verification-strategy is a skill published in the GitHub repository vstorm-co/pydantic-deepagents (1,059 stars, last pushed 17d ago), licensed MIT. It adds 13 tokens to every session and 656 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
Verification & Quality Assurance
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.
building-pydantic-ai-agents
Build AI agents with Pydantic AI — tools, capabilities (including on-demand loading), structured output, streaming, testing, and multi-agent patterns. Use when the user mentions Pydantic AI, imports pydanticai, or asks to build an AI agent, add tools/capabilities, defer capability loading, stream output, define agents…
test-reporting
Run the Level 2 dummy agent integration test suite and produce a detailed HTML report with per-test input → outcome analysis.
Vizra ADK Evaluation Framework
Test and evaluate AI agents with automated evaluations, assertions, and LLM-as-a-Judge patterns.
continuum-testing
Write tests for Continuum agents — mock LLM and memory clients via the DI Container, use fakeredis for sessions, snapshot agent responses, and run pytest-asyncio. Invoke when the user asks "test my agent", "mock the LLM", "fakeredis", "container injection", "pytest", or wants their CI to validate agent behavior…
continuum-evaluation
Evaluate agent quality with the EvaluatorAgent, generate golden datasets from a corpus, and run DeepEval/RAGAS metrics over conversations. Invoke when the user asks "test agent quality", "evaluate output", "RAG metrics", "DeepEval", "RAGAS", or "regression-test my agent".