pydantic-ai-harness: Agent for Claude Code

.agents/agents/docs-parity-reviewer.md

docs-parity-reviewer is an agent for Claude Code, Codex from pydantic/pydantic-ai-harness. It costs 65 tokens per session (1,212 once invoked), scanned A, original, MIT.

A documentation review agent for Pydantic AI Harness, a Python project for adding built-in capabilities to AI agents. It checks that a capability's README, unified documentation page, source code, examples, and links agree.

In plain words
What is it for?
Use it as a final review before merging a capability change, especially to check documentation parity, runnable snippets, source links, and the required page structure.
Why use it?
Documentation can become outdated or contain examples that no longer run, leaving users with incorrect instructions even when the code works.

Agent for Claude CodeCodex

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is pydantic/pydantic-ai-harness's own configuration. It tells Claude Code and Codex how to work on pydantic-ai-harness itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything pydantic-ai-harness configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/pydantic/pydantic-ai-harness/main/.agents/agents/docs-parity-reviewer.md
Clone the repo
git clone --depth 1 https://github.com/pydantic/pydantic-ai-harness

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for docs-parity-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/pydantic/pydantic-ai-harness/docs-parity-reviewer/github.svg)](https://agentmods.dev/agents/pydantic/pydantic-ai-harness/docs-parity-reviewer)
Your own site
<a href="https://agentmods.dev/agents/pydantic/pydantic-ai-harness/docs-parity-reviewer"><img src="https://agentmods.dev/badge/agents/pydantic/pydantic-ai-harness/docs-parity-reviewer/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.

agentmods 80×15 button for docs-parity-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/pydantic/pydantic-ai-harness/docs-parity-reviewer"><img src="https://agentmods.dev/badge/agents/pydantic/pydantic-ai-harness/docs-parity-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,212 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00065 $0.01212
Opus 5 $0.00032 $0.00606
Sonnet 5 $0.00013 $0.00242
Haiku 4.5 $0.00006 $0.00121

Measured 11d ago against content hash f18e3761e1b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

docs-parity-reviewer 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 11d 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.

.agents/agents/docs-parity-reviewer.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the documentation parity gate for pydantic-ai-harness. Every released capability ships two docs that must stay in sync with the code and with each other:

  • README -- pydantic_ai_harness/<capability>/README.md (or pydantic_ai_harness/experimental/acp/README.md for ACP). Serves GitHub and PyPI. Keeps absolute links and its badges.
  • Unified doc -- flat at docs/<capability>.md. Renders on the docs site (https://pydantic.dev/docs/ai/harness/). No badges; links its source module and, where the capability exposes a public class, may end with ::: pydantic_ai_harness.<Class> autodoc blocks. The sidebar is a flat list -- no capabilities/ or experimental/ subdirectories.

Both are hand-maintained. A change to one that is not reflected in the other is the failure mode you exist to catch.

What you are given

The diff or description of a capability change (the touched capability, and what its user-facing behavior now is). If you are not told which capability changed, infer it from the changed files under pydantic_ai_harness/.

Checks

Read the capability source, its README, and its unified doc, then report each problem as a finding (blocking / warning / nit) with a concrete fix.

  1. Both docs updated. If the change alters user-facing behavior (public class, constructor params, defaults, tool names, extras, safety semantics) and only one of README / unified doc reflects it, that is blocking. A doc describing behavior the code no longer has is also blocking.
  2. Snippets parse and run. Run uv run pytest tests/test_doc_snippets.py; this checks parsing and harness imports only. Execute every changed deterministic snippet unchanged. For snippets that need credentials or a live service, verify the complete runnable wrapper and require a fake-backed test for its control flow. Every block has all imports and capability wiring. Class names, params, and defaults match the source. Model ids are unchanged -- a changed model id is blocking. Illustrative signature pseudo-code uses {test="skip"}.
  3. README <-> unified doc consistency. The two agree on install extras, option names, defaults, and safety caveats. They need not be identical prose, but they must not contradict each other or the code.
  4. Links. Unified doc: harness-internal links are relative .md ([Shell](shell.md)); Pydantic AI links use root-relative internal paths /ai/<section>/<page>/ (not legacy ai.pydantic.dev links); no leftover ../../README.md, ../capabilities/, ../experimental/, or badge markup. README: absolute links are fine.
  5. Source link + API block. Every page links its source module (https://github.com/pydantic/pydantic-ai-harness/tree/main/pydantic_ai_harness/<module>/) so a reading agent can verify behavior -- a missing source link is a finding. Where the capability exposes a public class, the page may also end with a ## API reference section of ::: pydantic_ai_harness... autodoc blocks (auto-expanded from the docstring, not hand-written). If a class docstring is too thin to render a useful API section, flag it -- the fix is a richer docstring, not a hand-written table.
  6. Safety caveats preserved. Where the source carries access, sandbox, or command-control limits (Shell, CodeMode, FileSystem), both docs state them.
  7. Writing style. Both follow AGENTS.md "Writing style": no em-dashes (use --), no hype, plain ASCII punctuation.
  8. Purpose-first lead. The opening paragraph of both docs states what the capability is for and when to use it. An internal hook or class name (before_model_request, after_tool_execute, ...) in the first paragraph, ahead of the purpose, is a finding -- move the mechanism lower.
  9. Name matches the capability. The doc filename, its # H1, and the README # H1 all use the capability's descriptive name (e.g. "Overflowing Tool Output", not "Overflow"). A short or ClassName-style heading is a finding.
  10. Stability framing. Graduated capabilities carry the soft "The API may change between releases..." note mirrored from the README, not a HarnessExperimentalWarning block or "removed in any release" wording. ACP is the only page that keeps an !!! warning "Experimental".

Read the full file on GitHub · 87 lines

Changes

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.

  1. 11d ago First seen · 87 lines · 65 tokens per session scan A f18e3761e1b3

Subscribe to this mod's changes

docs-parity-reviewer is an agent published in the GitHub repository pydantic/pydantic-ai-harness (877 stars, last pushed today), licensed MIT. It adds 65 tokens to every session and 1,212 once invoked, about $0.0003 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.