Borrowing it
Nothing to install: this file belongs to vstorm-co/pydantic-ai-shields. 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/vstorm-co/pydantic-ai-shields/main/AGENTS.mdgit clone --depth 1 https://github.com/vstorm-co/pydantic-ai-shieldsWrote 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/instructions/vstorm-co/pydantic-ai-shields/agents-md)<a href="https://agentmods.dev/instructions/vstorm-co/pydantic-ai-shields/agents-md"><img src="https://agentmods.dev/badge/instructions/vstorm-co/pydantic-ai-shields/agents-md/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/instructions/vstorm-co/pydantic-ai-shields/agents-md"><img src="https://agentmods.dev/badge/instructions/vstorm-co/pydantic-ai-shields/agents-md.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 | $0.00417 | $0.00417 |
| Opus 5 | $0.00209 | $0.00209 |
| Sonnet 5 | $0.00083 | $0.00083 |
| Haiku 4.5 | $0.00042 | $0.00042 |
Grade A, and why
pydantic-ai-shields AGENTS.md 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
AGENTS.md
Instructions for AI coding assistants working on this repository.
Project Overview
pydantic-ai-shields provides guardrail capabilities for pydantic-ai agents. Built on pydantic-ai's native capabilities API (v1.71+). No middleware wrappers — pure capabilities.
Quick Reference
| Task | Command |
|---|---|
| Test | uv run pytest tests/ -v |
| Test + Coverage | uv run coverage run -m pytest tests/ && uv run coverage report --fail-under=100 |
| Lint | uv run ruff check src/ tests/ |
| Typecheck | uv run pyright src/ |
Architecture
src/pydantic_ai_shields/
__init__.py — Package exports
guardrails.py — 5 capability implementations + exceptions + CostInfo
tests/
test_guardrails.py — All tests
Capabilities
| Capability | Hooks Used | Purpose |
|---|---|---|
CostTracking |
before_run, after_run |
Token/USD tracking, budget enforcement |
ToolGuard |
prepare_tools, before_tool_execute |
Block tools, require approval |
InputGuard |
before_run |
Validate user input |
OutputGuard |
after_run |
Validate model output |
AsyncGuardrail |
wrap_run |
Concurrent guardrail + LLM |
Code Standards
- Coverage: 100% required
- Types: Pyright strict on src/
- Style: ruff for formatting and linting
Testing
from pydantic_ai import Agent
from pydantic_ai.models.test import TestModel
from pydantic_ai_shields import CostTracking, ToolGuard
agent = Agent(TestModel(), capabilities=[CostTracking()])
result = await agent.run("test")
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 · 54 lines · 417 tokens per session scan A 4e957a9f312d
pydantic-ai-shields AGENTS.md is an instructions file published in the GitHub repository vstorm-co/pydantic-ai-shields (92 stars, last pushed 25d ago), licensed MIT. It adds 417 tokens to every session, about $0.0021 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.