A Python type-checking tool that runs Pyright, reports errors by file, and guides fixes through a task list. Type checking finds places where code may use the wrong kind of value.

Use it to check a Python codebase, group errors, apply fixes one at a time, verify each file again, and optionally improve unclear data types.

It turns a large set of Python type errors into smaller, verifiable fixes instead of leaving the developer to sort through them manually.

pyright — Plugin for Claude Code by paulbaranowski/wild-horses

Install

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.

Clone the repo

git clone --depth 1 https://github.com/paulbaranowski/wild-horses

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/paulbaranowski/wild-horses/pyright/github.svg)](https://agentmods.dev/plugins/paulbaranowski/wild-horses/pyright)

Your own site

<a href="https://agentmods.dev/plugins/paulbaranowski/wild-horses/pyright"><img src="https://agentmods.dev/badge/plugins/paulbaranowski/wild-horses/pyright/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.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/paulbaranowski/wild-horses/pyright"><img src="https://agentmods.dev/badge/plugins/paulbaranowski/wild-horses/pyright.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 1 command cost 65 tokens a session between them.

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.

Security

Grade A, and why

pyright 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 2mo 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.

plugins/pyright/.claude-plugin/plugin.json · 9 lines

What it actually says

{
  "name": "pyright",
  "description": "Run pyright on a Python codebase and fix the errors it finds via the harness task-list pipeline. Phase 3 partitions errors per-file into a structured markdown report; Phase 4 hands off to the sibling task-list-builder + task-list-runner skills for serial, audited fixes with per-task pyright <file> verifySteps and intent-keyed agentValidations templates. Supports strictness override (basic/standard/strict), persisting the level to config, progressive ratcheting, fix-intent selection (silence/improve/bugs-only), an end-of-run list of suggested type improvements, active TypedDict/Pydantic extraction from opaque dict[str, Any] under --intent improve, and a handoff pointer to /harness:reasoning-gaps.",
  "version": "1.12.1",
  "author": {
    "name": "Paul Baranowski"
  }
}

Contents

What it installs

The manifest is a name and a version. 1 command travel with it, and installing the plugin installs all of them — 65 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Command run-and-fix A 65 tokens

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.

2mo ago First seen · 9 lines scan A 1228ec00f317

Subscribe to this mod's changes

pyright is a plugin published in the GitHub repository paulbaranowski/wild-horses (14 stars, last pushed 14d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.

Debugging Languages Python

pyright next to 6 plugins from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
pyrightpaulbaranowski/wild-horses	Plugin	14	14d ago	MIT	A	—	Claude Code
code-qualitysam-dumont/claude-skills	Plugin	38	6d ago	MIT	A	—	Claude Code
typemux-ccK-dash/typemux-cc	Plugin	17	yesterday	MIT	A	—	Claude Code
python-lspMSApps-Mobile/claude-plugins	Plugin	11	today	MIT	A	—	Claude Code
ida-plugin-developmentHexRaysSA/claude-marketplace	Plugin	122	2mo ago	MIT	A	—	Claude Code
pyeyeokeefeco/pyeye-mcp	Plugin	0	yesterday	MIT	A	—	Claude Code
claude-aaiAnswerDotAI/skill-plugins	Plugin	5	3mo ago	Apache-2.0	A	—	Claude Code