← Back to Skills Marketplace
singggggyee

Agent Rule Pilot

by SingYee · GitHub ↗ · v1.0.0 · MIT-0
macoslinux ✓ Security Clean
102
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install agent-rule-pilot
Description
Say 'sync my agent configs' to write coding rules once and sync to Claude Code, Cursor, Copilot, Windsurf, and 4 more agents.
README (SKILL.md)

Rule Pilot

You use Claude Code, Cursor, Copilot, and other AI agents — but each has its own config file. Edit one, the others go stale. This skill keeps them all in sync from a single RULES.md.

Quick start

Just say:

  • "sync my agent configs" — sync RULES.md to all your AI agents
  • "check config drift" — see which configs have gone out of sync
  • "create RULES.md" — generate a starter rules file for your project
  • "convert CLAUDE.md to cursorrules" — one-off format conversion

Supported agents (8)

Agent Config file
Claude Code CLAUDE.md
Cursor .cursorrules
GitHub Copilot .github/copilot-instructions.md
Windsurf .windsurfrules
Aider .aider.conf.yml
Codex CLI AGENTS.md
Cody .sourcegraph/cody.json
Continue.dev .continuerc.json

Links

Below are instructions for Claude Code. You can ignore this section.

Instructions

Detect which agent configs exist, then pick the right mode:

RULES.md exists → Sync to all agent configs. Each agent gets common rules + agent-specific extensions (e.g., Claude Code gets "use Read not cat"). Show diff before writing.

No RULES.md, but configs exist → Reverse-extract common rules into a new RULES.md. Flag conflicts. Ask user to resolve.

Nothing exists → Detect language from package.json/Cargo.toml/pyproject.toml/go.mod, generate opinionated RULES.md.

Drift check → Compare configs against RULES.md or each other. Report which are in sync, which diverged.

Per-agent overrides: RULES.md supports \x3C!-- agent:xxx --> / \x3C!-- /agent:xxx --> markers for agent-specific rules.

Rules: Always show diffs before writing. Preserve agent-specific sections not in RULES.md. Only generate configs for agents the user actually uses. Validate output format (JSON, YAML).

Usage Guidance
This skill will read and write multiple local configuration files and project manifests (RULES.md, CLAUDE.md, .cursorrules, .github/copilot-instructions.md, .sourcegraph/cody.json, etc.). That behavior is coherent with its purpose, but before using it: (1) review the linked GitHub repo to verify the code/author if you plan to trust it; (2) keep backups or make a git commit before running the sync so you can revert unintended edits; (3) confirm the agent actually shows diffs and asks for confirmation before writing (the SKILL.md says it will); (4) prefer running it in a safe/test repository first; and (5) be mindful that, while it asks for no credentials or network access, the agent will still modify files on your system—only proceed if you trust the skill and monitor the first run.
Capability Analysis
Type: OpenClaw Skill Name: agent-rule-pilot Version: 1.0.0 The Agent Rule Pilot skill is a utility designed to synchronize project-specific coding rules across multiple AI agent configuration files (e.g., .cursorrules, CLAUDE.md, .windsurfrules). The instructions in SKILL.md focus on file management and format conversion, including safety measures such as requiring the agent to show diffs before writing changes and preserving existing sections. No indicators of data exfiltration, malicious execution, or harmful prompt injection were found.
Capability Assessment
✓ Purpose & Capability
The skill's name and description promise syncing agent rules across multiple AI agent config files; the SKILL.md explicitly describes detecting existing configs, reading package manifests (package.json, Cargo.toml, etc.), generating RULES.md, and writing per-agent config files. All of those capabilities are directly relevant to the stated purpose.
ℹ Instruction Scope
Instructions require reading and writing multiple local config files and project manifests, and performing diffs and format validation. This is expected for a sync tool, but it does mean the agent will access many repository/dotfile paths and modify them. The SKILL.md states 'show diffs before writing' and 'ask user to resolve' conflicts, which mitigates risk as long as the agent actually prompts before changes. The SKILL.md does not instruct any network exfiltration or access to unrelated secrets.
✓ Install Mechanism
There is no install spec and no code files—this is an instruction-only skill. That is the lowest-risk install posture and matches the content of the SKILL.md.
ℹ Credentials
The skill requests no environment variables, credentials, or installs. However, it will access a number of well-known config paths (agent dotfiles and project manifests). The registry metadata does not enumerate required config paths; users should be aware the skill will read and write those files in the workspace/home directories.
✓ Persistence & Privilege
The skill is not marked always:true and does not request system-wide or other-skills' configuration changes. Autonomous invocation is allowed (normal default); this means the agent could run the sync flow on request or potentially autonomously, but that is expected for a tool that manipulates local files.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install agent-rule-pilot
  3. After installation, invoke the skill by name or use /agent-rule-pilot
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release
Metadata
Slug agent-rule-pilot
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Agent Rule Pilot?

Say 'sync my agent configs' to write coding rules once and sync to Claude Code, Cursor, Copilot, Windsurf, and 4 more agents. It is an AI Agent Skill for Claude Code / OpenClaw, with 102 downloads so far.

How do I install Agent Rule Pilot?

Run "/install agent-rule-pilot" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Agent Rule Pilot free?

Yes, Agent Rule Pilot is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Agent Rule Pilot support?

Agent Rule Pilot is cross-platform and runs anywhere OpenClaw / Claude Code is available (macos, linux).

Who created Agent Rule Pilot?

It is built and maintained by SingYee (@singggggyee); the current version is v1.0.0.

More Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191115 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 Comments