A workflow guide for Rush, a local toolbelt that runs linters, type checkers, tests, and security scanners and returns structured results.

Use it after code changes, before commits, or when checking formatting, types, tests, security, secrets, or unused code.

It makes code checks part of the normal workflow and tells the agent to report or fix warnings and failures instead of guessing about code quality.

rush — Skill for Claude Code by jamesdsizemore/rush-cli

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.

Any agent

npx skills add jamesdsizemore/rush-cli --skill rush

Clone the repo

git clone --depth 1 https://github.com/jamesdsizemore/rush-cli

Made for: Claude Code.

Or install rush, the plugin that ships this one along with the rest of its 1 skill, 1 hook, 1 MCP server.

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/skills/jamesdsizemore/rush-cli/rush/github.svg)](https://agentmods.dev/skills/jamesdsizemore/rush-cli/rush)

Your own site

<a href="https://agentmods.dev/skills/jamesdsizemore/rush-cli/rush"><img src="https://agentmods.dev/badge/skills/jamesdsizemore/rush-cli/rush/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/skills/jamesdsizemore/rush-cli/rush"><img src="https://agentmods.dev/badge/skills/jamesdsizemore/rush-cli/rush.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,006 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.

Model	Per session	Once invoked
Fable 5.1	$0.00073	$0.02006
Opus 5.5	$0.00029	$0.00802
Sonnet 5.5	$0.00015	$0.00401
Haiku 4.5	$0.00007	$0.00201

Measured 3d ago against content hash fa48967692cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

rush 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 3d 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.

src/rush/integrations/agent_assets/claude/skills/rush/SKILL.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Rush

Rush is a local code-quality toolbelt. It runs installed engines (linters, type checkers, test runners, security scanners) and returns one structured result per call: {status, findings, summary, raw}.

Triggers

Call Rush:

Before every commit: run rush_check on the project and fix or report every fail and warn before committing.
After every code change: run rush_check, or rush_lint on the changed files, before saying the change is done.
When the user asks about code quality, lint, formatting, types, tests, security, secrets or dead code: run the matching Rush tool instead of guessing.

Profiles

core (new registrations run rush mcp serve --profile core) exposes exactly seven tools: rush_status, rush_check, rush_lint, rush_review, rush_security, rush_test, rush_memory.
full (rush mcp serve --profile full, and every older registration without --profile) keeps every existing tool name and alias plus rush_status and rush_check. The server's own tool list is the full list; read it instead of assuming a tool exists.
A tool that is not in the connected profile fails as an unknown tool. The profile limits which tools are listed; it never grants a permission.

Paths

Not every tool takes a path. Read each tool's input schema.
A relative path resolves against the declared project root. Declare it with project (a registered project path) or project_id. With no declared root, a relative path resolves against the directory the MCP server started in.
Absolute paths keep their identity. Rush never follows a symlink out of the project root.
Project memory, cache and results live under the resolved project root.

Statuses

Status	Meaning
`ok`	The requested work ran and found nothing to report.
`warn`	The work ran and found problems, or required work ran only partly.
`fail`	The work ran and found blocking problems.
`error`	Rush or an engine failed to run; the result says why.
`skipped`	No work was performed: the engine is missing, there were no supported targets, or a permission was denied.

Read the full file on GitHub · 188 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.

3d ago First seen · 188 lines · 73 tokens per session scan A fa48967692cf

Subscribe to this mod's changes

rush is a skill published in the GitHub repository jamesdsizemore/rush-cli (0 stars, last pushed 2d ago), licensed MIT. It adds 73 tokens to every session and 2,006 once invoked, about $0.0003 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 2026-10-15.

Security Testing Unit testing

test-master

Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…

Jeffallan/claude-skills · 104 tokens

migrate-xunit-to-xunit-v3

Migrate .NET test projects from xUnit.net v2 to xunit.v3 and fix v3 breaks. Use for package/CPM conversion, OutputType=Exe, preserving the VSTest or MTP runner (including projects currently using YTest.MTP.XUnit2), incompatible TFMs, async void tests, string-to-Type attributes, custom Fact/Theory/BeforeAfterTest…

dotnet/skills · 149 tokens

rush