Borrowing it
Nothing to install: this file belongs to pydantic/pydantic-ai-harness. 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-harness/main/AGENTS.mdgit clone --depth 1 https://github.com/pydantic/pydantic-ai-harnessWrote 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/pydantic/pydantic-ai-harness/agents-md)<a href="https://agentmods.dev/instructions/pydantic/pydantic-ai-harness/agents-md"><img src="https://agentmods.dev/badge/instructions/pydantic/pydantic-ai-harness/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/pydantic/pydantic-ai-harness/agents-md"><img src="https://agentmods.dev/badge/instructions/pydantic/pydantic-ai-harness/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 | $0.03151 | $0.03151 |
| Opus 5.5 | $0.01260 | $0.01260 |
| Sonnet 5.5 | $0.00630 | $0.00630 |
| Haiku 4.5 | $0.00315 | $0.00315 |
Grade A, and why
pydantic-ai-harness 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 1mo 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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pydantic AI Harness
Repository purpose
pydantic-ai-harness is the first-party capability library for Pydantic AI.
Pydantic AI core owns the primitive runtime: agent loop semantics, normalized messages, model/provider/profile behavior, tool execution semantics, durable execution primitives, and generic capability hooks.
Harness owns optional, batteries-included compositions built from those primitives: coding-agent tools, guardrails, memory, context management, repo tools, verification loops, skills, planning, sub-agents, and other reusable agent behaviors.
When a change needs new core semantics, stop and propose the Pydantic AI core change instead of reimplementing core behavior in harness.
Vocabulary
- Capability: an
AbstractCapabilitysubclass that bundles tools, hooks, instructions, and model settings into a reusable unit. This is the core abstraction of pydantic-ai-harness. - Hook: a lifecycle method on
AbstractCapabilitythat intercepts agent graph execution (e.g.before_model_request,wrap_run,after_tool_execute) - Toolset: a collection of tools that a capability can provide to the agent
- Guard: a type of capability that validates inputs/outputs or controls tool access (e.g.
InputGuard,OutputGuard) - Harness: this package -- a collection of pre-made capabilities for Pydantic AI.
- AICA: AI Code Assistant -- the automated agent that implements issues, reviews plans, and handles PR feedback
- Ralph loop: the state-machine-based workflow that drives AICA through phases (TRIAGE -> GOALS -> PLAN -> CODE -> VERIFY -> REVIEW -> PUBLISH)
- DDD+ protocol: classification system for PR review comments (do, dismiss, discuss, waiting, done)
AICA preflight
Before implementing or reviewing a capability change:
- Read
agent_docs/index.md. - Read the linked
agent_docs/guide for the task. - Read the public Pydantic AI docs for every integration point you touch:
- capabilities: https://pydantic.dev/docs/ai/capabilities/overview/
- hooks: https://pydantic.dev/docs/ai/core-concepts/hooks/
- toolsets: https://pydantic.dev/docs/ai/tools-toolsets/toolsets/
- advanced tools: https://pydantic.dev/docs/ai/tools-toolsets/tools-advanced/
- agents: https://pydantic.dev/docs/ai/core-concepts/agent/
- testing: https://pydantic.dev/docs/ai/guides/testing/
- Inspect the installed
pydantic_aipackage source for exact hook/toolset signatures when needed. Do not assume a contributor's local checkout layout. - Use
pydantic_ai_harness.code_modeas the exemplar for capability shape, docs, tests, and public exports until another capability becomes a better example. Capabilities live in their own top-level submodulepydantic_ai_harness/<name>/(module name = capability name; one module per capability or strategy) and are not re-exported from the root__init__.py, so each keeps its own optional dependencies. Theexperimentaltier is retired; ACP is the sole remaining experimental capability (seeagent_docs/capability-authoring.md, "Capability Submodules And Exports").
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.
- 1mo ago Changed · +24 lines · +283 tokens per session 5dddc346b2a0
- 1mo ago Changed · +5 lines · +84 tokens per session 3bc59ee20455
- 1mo ago Changed · +14 lines · +133 tokens per session 2c8b07bf8d4f
- 1mo ago First seen · 203 lines · 2,651 tokens per session scan A b9c7a30e00a0
pydantic-ai-harness AGENTS.md is an instructions file published in the GitHub repository pydantic/pydantic-ai-harness (957 stars, last pushed 22d ago), licensed MIT. It adds 3,151 tokens to every session, about $0.0126 per session on Opus 5.5. 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
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
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.