What is arc1-cursor-regression?

A Cursor setup and prompt generator for regression checks in ARC-1, a software project. It builds checks from a pull request, chat findings, or changed files.

Use it to create Cursor MCP configuration, prepare the environment, and generate prompts for checking a pull request, bug fix, or feature.

It avoids writing the same generic test checklist for every change. The checks focus on the features or fixes that actually changed.

How arc-mcp/arc-1 configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to arc-mcp/arc-1. 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/arc-mcp/arc-1/main/.claude/skills/arc1-cursor-regression/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/arc-mcp/arc-1

Made for: Claude Code.

Or install arc-1, the plugin that ships this one along with the rest of its 24 skills, 8 commands, 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/arc-mcp/arc-1/arc1-cursor-regression/github.svg)](https://agentmods.dev/skills/arc-mcp/arc-1/arc1-cursor-regression)

Your own site

<a href="https://agentmods.dev/skills/arc-mcp/arc-1/arc1-cursor-regression"><img src="https://agentmods.dev/badge/skills/arc-mcp/arc-1/arc1-cursor-regression/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/arc-mcp/arc-1/arc1-cursor-regression"><img src="https://agentmods.dev/badge/skills/arc-mcp/arc-1/arc1-cursor-regression.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,073 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	$0.00000	$0.04073
Opus 5	$0.00000	$0.02037
Sonnet 5	$0.00000	$0.00815
Haiku 4.5	$0.00000	$0.00407

Measured 9d ago against content hash 953a436a1ea1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

arc1-cursor-regression 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.

.claude/skills/arc1-cursor-regression/SKILL.md · 373 lines

How it starts

The opening of the file, as written. The whole thing — 373 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ARC-1 Cursor Regression Skill (Generic + Adaptive)

This skill creates tailored Cursor setup and prompts based on:

PR scope (preferred)
Current chat findings
Changed files in the local branch

It must not output a hardcoded one-scenario checklist unless the user explicitly asks for that.

Trigger conditions

Use this skill when user asks for:

Cursor MCP setup for ARC-1
Regression prompts
“verify this PR/fix/feature” prompts
“create config + prompts so I can run quickly”
“run the env prep for me”

Composite request shortcut (must support)

If the user asks in one message to:

use this skill
derive tests from chat + current branch diff
generate config + env prep + one execution prompt
and says “run the env prep for me”

then treat it as a single composite workflow:

Resolve target root/worktree/branch.
Derive module set from diff + chat.
Generate config + one copy/paste execution prompt.
Execute env prep commands immediately in the resolved root.
Report env prep execution status (success/failure + minimal fix if failed).

Required discovery workflow

0) Resolve active ARC-1 root + branch/worktree (mandatory)

Always bind generated config/scripts/prompts to the actual target repo root (not a remembered path).

Run:

git rev-parse --show-toplevel
git branch --show-current
git worktree list --porcelain

Rules:

If user gave a PR/branch, ensure the resolved root/branch matches that target.
If multiple ARC-1 clones/worktrees exist, explicitly choose the one containing the target branch/commit.
Never hardcode /Users/.../DEV/arc-1 unless user explicitly requests that exact path.

0.5) Confirm active Cursor project/workspace matches target root (mandatory for runtime runs)

Before generating runtime prompts, ensure the Cursor chat session is attached to the same project/workspace that will host MCP servers and tool cache for the resolved root.

Rules:

If the active Cursor project path differs from the resolved ARC-1 root, classify immediately as Environment/session setup issue (not code regression) and provide a fix: open the correct workspace and reconnect MCP.
Do not mix artifacts from different Cursor projects when evaluating server availability/schema.

Read the full file on GitHub · 373 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.

9d ago First seen · 373 lines · 0 tokens per session scan A 953a436a1ea1

Subscribe to this mod's changes

arc1-cursor-regression is a skill published in the GitHub repository arc-mcp/arc-1 (183 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,073 tokens. 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.

Testing

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

arc-1: Skill for Claude Code