creating-continue-packages

A guide for creating Continue rules, which are markdown instructions that the Continue coding assistant applies globally or when files match selected patterns.

In plain words
What is it for?
It helps create rules for specific file types or folders, define always-on instructions, and document standards such as documentation practices.
Why use it?
It explains the required configuration fields and matching behavior, reducing the chance that rules are ignored or applied in the wrong places.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/pr-pm/prpm/creating-continue-packages
Any agent
npx skills add pr-pm/prpm --skill creating-continue-packages
Clone the repo
git clone --depth 1 https://github.com/pr-pm/prpm

Made for: Claude Code, Codex.

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,681 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00033 $0.01681
Opus 5 $0.00016 $0.00840
Sonnet 5 $0.00007 $0.00336
Haiku 4.5 $0.00003 $0.00168

Measured 3d ago against content hash b73dcd99c77d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

creating-continue-packages 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.

.claude/skills/creating-continue-packages/SKILL.md · 301 lines

How it starts

The opening of the file, as written. The whole thing — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Creating Continue Packages

Overview

Continue uses markdown files with YAML frontmatter in .continuerules/*.md or YAML configuration in config.yaml. Rules are context-aware using glob patterns, regex matching, or always-applied globally.

CRITICAL: The name field is REQUIRED in frontmatter (unlike other formats where it's optional).

Quick Reference

Required Frontmatter

---
name: Rule display name (REQUIRED)
---

Optional Frontmatter

description: Description of when rule should be used
globs: "**/*.{ts,tsx}"  # String or array
regex: "^import .* from '.*';$"  # String or array
alwaysApply: true  # true, false, or undefined
version: "1.0.0"
schema: "v1"

AlwaysApply Semantics

Value Behavior
true Always included, regardless of context
false Included if globs match OR agent decides based on description
undefined (default) Included if no globs exist OR globs match

Creating Rules with Globs

Glob patterns match file paths:

---
name: Documentation Standards
globs: docs/**/*.{md,mdx}
alwaysApply: false
description: Standards for writing and maintaining documentation
---

# Documentation Standards

## Structure

- Follow consistent heading hierarchy starting with h2 (##)
- Include YAML frontmatter with title, description, and keywords
- Use descriptive alt text for images

## Writing Style

- Keep paragraphs concise and scannable
- Use code blocks with appropriate language tags
- Include cross-references to related documentation

Glob Patterns (String or Array)

# Single pattern (string)
globs: "**/*.{ts,tsx}"

# Multiple patterns (array)
globs:
  - "src/**/*.ts"
  - "tests/**/*.ts"

Creating Rules with Regex

Regex patterns match file content:

---
name: React Component Standards
regex: "^import React"
globs: "**/*.{tsx,jsx}"
alwaysApply: false
description: Standards for React component development
---

# React Component Standards

## Component Structure

- Use functional components with hooks
- Keep components under 200 lines
- Extract logic into custom hooks when appropriate
- Co-locate styles with components

## Examples

\`\`\`typescript
// Good: Focused component
function UserProfile({ userId }: Props) {
  const user = useUser(userId);
  return <div>{user.name}</div>;
}
\`\`\`

Read the full file on GitHub · 301 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. 3d ago First seen · 301 lines · 33 tokens per session scan A b73dcd99c77d

Subscribe to this mod's changes

creating-continue-packages is a skill published in the GitHub repository pr-pm/prpm (120 stars, last pushed 2mo ago), licensed MIT. It adds 33 tokens to every session and 1,681 once invoked, about $0.0002 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.