Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/kanyun-inc/reskillnpx agentmods add rules/kanyun-inc/reskill/developmentWrote 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.
[](https://agentmods.dev/rules/kanyun-inc/reskill/development)<a href="https://agentmods.dev/rules/kanyun-inc/reskill/development"><img src="https://agentmods.dev/badge/rules/kanyun-inc/reskill/development/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.
<a href="https://agentmods.dev/rules/kanyun-inc/reskill/development"><img src="https://agentmods.dev/badge/rules/kanyun-inc/reskill/development.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.02822 | $0.02822 |
| Opus 5.5 | $0.01129 | $0.01129 |
| Sonnet 5.5 | $0.00564 | $0.00564 |
| Haiku 4.5 | $0.00282 | $0.00282 |
Grade A, and why
development 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 396 lines — stays where its author put it; the contents beside it link to each section on GitHub.
reskill Development Rules
Project Overview
reskill is a Git-based package manager for AI agent skills, similar to npm/Go modules. It provides declarative configuration, version locking, and seamless synchronization for managing skills across projects and teams.
Supported AI Agents: Cursor, Claude Code, Codex, OpenCode, Windsurf, GitHub Copilot, and more.
Tech Stack
- Language: TypeScript (ES Modules)
- Runtime: Node.js >= 18.0.0
- Build Tool: Rslib (Rspack-based library bundler)
- Testing: Vitest with @vitest/coverage-v8
- CLI Framework: Commander.js
- Linting/Formatting: Biome
- Package Manager: pnpm
Code Style Guidelines
Language Requirements
- Primary Language: English
- Comments: Must be in English only, no Chinese comments allowed
- Variable/Function Names: Use English, camelCase for variables and functions
- Class Names: PascalCase
- File Names: kebab-case for files, e.g.,
skill-manager.ts
TypeScript Standards
- Use strict TypeScript configuration
- Prefer
typeoverinterfacefor simple type aliases - Use explicit return types for public functions
- Use
readonlyfor immutable properties - Avoid
anytype, useunknownwith type guards instead
// Good
export function parseRef(ref: string): ParsedSkillRef { ... }
// Avoid
export function parseRef(ref: string) { ... }
Import Order
- Node.js built-in modules (with
node:prefix) - External dependencies
- Internal modules (relative imports)
import * as path from 'node:path';
import * as fs from 'node:fs';
import { Command } from 'commander';
import semver from 'semver';
import { SkillManager } from '../core/skill-manager.js';
import type { InstalledSkill } from '../types/index.js';
Error Handling
- Use descriptive error messages in English
- Throw typed errors when possible
- Log errors with appropriate log levels
- Always clean up resources in error cases
// Good
if (!exists(skillPath)) {
throw new Error(`Skill ${name} not found at ${skillPath}`);
}
// Log for user feedback
logger.error(`Failed to install ${name}: ${error.message}`);
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.
- 1mo ago First seen · 396 lines · 2,822 tokens per session scan A 2293f30ad800
development is a cursor rule published in the GitHub repository kanyun-inc/reskill (60 stars, last pushed 28d ago), licensed MIT. It adds 2,822 tokens to every session, about $0.0113 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 2026-08-30.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
config-validation-and-normalization
Config validation and normalization responsibilities (defineConfig normalizes, the orm section schema validates and resolves paths, the loader reports per-section diagnostics).
control-plane-descriptors
Control plane descriptor and instance implementation patterns.