Agent skill

Rpa Gen Rules

by coddy-project in coddy-project/coddy-agent

A skill your agent uses when the user invokes /rpa-gen-rules or asks to create, refresh, audit, or synchronize project instructions such as root AGENTS.md, Cursor .cursor/rules, or Claude Code…

MITAuto-check passedProductivity & Automation

Install Rpa Gen Rules

skills CLI
$ npx skills add coddy-project/coddy-agent --skill rpa-gen-rules -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install coddy-project/coddy-agent rpa-gen-rules --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/coddy-project/coddy-agent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/internal/skills/bundled/rpa-gen-rules .claude/skills/rpa-gen-rules && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
rpa-gen-rules
GitHub stars
168
Token cost
~1.2k tokens
SKILL.md length
579 words
Files
23 (incl. references)
Skills in repo
6
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when the user invokes /rpa-gen-rules or asks to create, refresh, audit, or synchronize project instructions such as root AGENTS.md, Cursor .cursor/rules, or Claude Code…

  • Works in 6 steps: Inventory root instructions, rule trees,… → choose only hosts the repository uses or… → write architecture boundaries, real… → …
  • The user invokes /rpa-gen-rules
  • SKILL.md covers Goal, Read progressively, Workflow and Quick reference, plus 4 more sections
  • Runs Python scripts from its folder

What it does

Rpa Gen Rules is an agent skill from coddy-project/coddy-agent. Use when the user invokes /rpa-gen-rules or asks to create, refresh, audit, or synchronize project instructions such as root AGENTS.md, Cursor .cursor/rules, or Claude Code .claude/rules, especially when existing rule trees have drifted.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 29 other files, including reference files (for example `README.md`, `references/bdd-and-agents.md` and `references/claude-examples/.claude/CLAUDE.md`).

It sits in Productivity & Automation, covering Agent instruction files and Workflow automation. The repository describes itself as: General-purpose agent in one static Go binary: console TUI, ACP server for editors, OpenAI-compatible API with embedded web UI, Telegram gateway, cron scheduler, swarm relay… The licence is MIT.

When your agent uses it

  • The user invokes /rpa-gen-rules
  • Synchronize project instructions such as root AGENTS.md
  • Cursor .cursor/rules
  • Claude Code .claude/rules

Example prompts

  • “/rpa-gen-rules”

Requirements

  • Python 3

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Inventory root instructions, rule trees, architecture docs, tests, build files, and CI;
  2. choose only hosts the repository uses or the user requests;
  3. write architecture boundaries, real verification commands, security invariants, and documentation duties in repository terms;
  4. create scoped native rules without widening their activation;
  5. synchronize deliberate mirrors and install the Codex hook when Codex is in scope;
  6. run repository checks, probe adapters, verify symlinks, and report limitations honestly.

What it can do on your machine

Read from SKILL.md and the folder at commit db3720a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships script files (Python, from the files we listed), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Rpa Gen Rules loads about 1.2k tokens when it runs, and up to ~15k if it reads all its reference files. Until then it costs about 63 tokens; SKILL.md has 579 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~63
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~15k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from coddy-project/coddy-agent at commit db3720a, republished under its MIT licence (© coddy-project). 579 words, ~1,213 tokens.

Download SKILL.mdSave it as .claude/skills/rpa-gen-rules/SKILL.md (or your agent's skills folder). This skill also uses 22 other files; get the full folder from GitHub.
name
rpa-gen-rules
description
Use when the user invokes /rpa-gen-rules or asks to create, refresh, audit, or synchronize project instructions such as root AGENTS.md, Cursor .cursor/rules, or Claude Code .claude/rules, especially when existing rule trees have drifted.
metadata.version
1.3.4

Generate project rules

Goal

Create project instructions for the coding-agent hosts the repository actually supports.

  • Keep repository-wide policy in root AGENTS.md;
  • enforce layered implementation from lower dependencies upward;
  • require RED-GREEN-REFACTOR for behavior changes;
  • use native Cursor and Claude Code formats accurately;
  • let the Codex project hook attach Cursor rules without duplicating their bodies;
  • never promise another host equivalent scoped delivery without a test.

Infer the contract from code, tests, docs, builds, and CI. Ask only when a real product decision is missing. Generated instruction files default to English unless the user or repository defines another language.

Read progressively

  • references/bdd-and-agents.md - BDD wording, host behavior, synchronization, and limitations;
  • references/cursor-examples/.cursor/rules/ and references/claude-examples/.claude/ - native templates;
  • references/codex-examples/.codex/hooks.json and hooks/attach_rules.py - Codex adapter templates.

Workflow

  1. Inventory root instructions, rule trees, architecture docs, tests, build files, and CI;
  2. choose only hosts the repository uses or the user requests;
  3. write architecture boundaries, real verification commands, security invariants, and documentation duties in repository terms;
  4. create scoped native rules without widening their activation;
  5. synchronize deliberate mirrors and install the Codex hook when Codex is in scope;
  6. run repository checks, probe adapters, verify symlinks, and report limitations honestly.

Quick reference

SurfaceGenerated outputRole
Commonroot AGENTS.mdrepository-wide baseline
Claude compatibilityCLAUDE.md symlink or short importsame top-level policy
Cursor.cursor/rules/*.mdcnative Cursor rules and Codex hook input
Claude Code.claude/rules/*.mdnative Claude Code rules
Codexroot AGENTS.md, .codex/hooks.json, .codex/hooks/attach_rules.pycommon policy plus project adapter
Other hostsexisting, documented integrationno invented adapter

Cursor and Claude Code mapping

  • Claude rule without paths -> Cursor alwaysApply: true without a narrowing glob;
  • Claude paths -> Cursor globs with alwaysApply: false;
  • Cursor globs with alwaysApply: false -> Claude paths;
  • keep paired bodies equivalent and adapt only metadata and host-specific links.

Never map a path-scoped rule to alwaysApply: true.

Show full SKILL.md (283 more words)Show less

Codex (AGENTS.md + project hook)

Root AGENTS.md carries common policy. The project hook reads .cursor/rules/*.mdc and attaches rules for supported Codex events and edit payloads.

  1. Copy the bundled hooks.json and hooks/attach_rules.py templates;
  2. keep Cursor rules as the hook input and do not copy their bodies under .codex;
  3. Do not generate .codex/rules.md; it is not model context and becomes a stale index;
  4. probe scalar and YAML-list globs plus add, update, delete, rename, Edit, and Write payloads;
  5. tell the user to run /hooks once per clone and after either hook file changes.

The hook attaches always-on rules at SessionStart and recognized scoped rules at PreToolUse. It is fail-open project code, not native Codex rule discovery or a security boundary. Keep critical constraints in root policy, permissions, code, tests, or CI. Codex execpolicy .rules are unrelated command policy.

Rules Sync

Keep root AGENTS.md aligned with its compatibility entrypoints. Update deliberate Cursor and Claude Code mirrors together, with equivalent bodies and native metadata. The Codex hook reads the Cursor representation directly and needs no manual index. Label intentional host-specific differences.

Every generated workflow rule must carry this contract.

Common mistakes

MistakeCorrection
Generate .codex/rules.mdDo not generate it; the hook reads Cursor rules directly
Copy Cursor bodies into .codexKeep one Cursor body
Call a vendor tree universally canonicalDescribe its native role and explicit adapters
Map Claude paths to alwaysApply: trueUse Cursor globs with alwaysApply: false
Put a security boundary only in scoped model contextEnforce it outside the scoped rule too
Invent OpenCode, ZCode, .agents, or .coddy deliveryPreserve a tested project integration or research it separately
Copy historical PR state into standing rulesExtract and verify the current invariant

© coddy-project, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 22 other files (references) in internal/skills/bundled/rpa-gen-rules of coddy-project/coddy-agent.

  • SKILL.md
  • LICENSE
  • README.md
  • references/bdd-and-agents.md
  • references/claude-examples/.claude/CLAUDE.md
  • references/claude-examples/.claude/rules/api-layer.md
  • references/claude-examples/.claude/rules/architecture.md
  • references/claude-examples/.claude/rules/code-style.md
  • references/claude-examples/.claude/rules/implementation-order.md
  • references/claude-examples/.claude/rules/testing.md
  • references/claude-examples/.claude/rules/workflow.md
  • references/codex-examples/.codex/hooks.json
  • references/codex-examples/.codex/hooks/attach_rules.py
  • references/cursor-examples
  • … and 9 more

Open the folder on GitHubat commit db3720a

Compare with similar skills

Rpa Gen Rules next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Rpa Gen Rules compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Rpa Gen Rules this skillcoddy-project/coddy-agent168—~1.2kAutomated safety check: PassMIT
Warp Factory Fileswarpdotdev/warp65k1 repos~2.5kAutomated safety check: PassAGPL-3.0
Fastgpt Workflow GeneratorYYH211/Claude-meta-skill282—~5.5kAutomated safety check: PassMIT
Browser4 Pluginplatonai/Browser41.2k—~3.6kAutomated safety check: PassApache-2.0
Lindy Core Workflow Bjeremylongshore/tons-of-skills-marketplace2.8k—~1.6kAutomated safety check: PassMIT
Refly Skill Runnerrefly-ai/refly7.5k—~1.7kAutomated safety check: PassCustom licence

Similar skills

  • Warp Factory Files

    warpdotdev/warp

    Authors and edits file-based Warp software factory definitions rooted at factory.yaml, covering agents, automations, scorers and webhooks, and validates them before a pull request.

    65k GitHub starsUsed in 1 repo~2.5k tokens
    DevelopmentAuto-check passed
  • Fastgpt Workflow Generator

    YYH211/Claude-meta-skill

    Generates production-ready FastGPT workflow JSON from natural language requirements.

    282 GitHub stars~5.5k tokensUpdated 4 mo ago
    Productivity & AutomationAuto-check passed
  • Browser4 Plugin

    platonai/Browser4

    Guides the creation of Browser4 plugins from requirements gathering through deployment.

    1.2k GitHub stars~3.6k tokensUpdated yesterday
    Productivity & AutomationAuto-check passed
  • Lindy Core Workflow B

    jeremylongshore/tons-of-skills-marketplace

    Configure Lindy triggers, scheduling, multi-agent delegation, and automation.

    2.8k GitHub stars~1.6k tokensUpdated yesterday
    Productivity & AutomationAuto-check passed
  • Refly Skill Runner

    refly-ai/refly

    Base skill for the Refly ecosystem: finds, runs and monitors workflow-backed skills through the refly command line, with the actual work done on the Refly backend.

    7.5k GitHub stars~1.7k tokensUpdated 2 mo ago
    Productivity & AutomationAuto-check passed
  • Piece Builder

    activepieces/activepieces

    Build and edit Activepieces pieces (integrations) — creating new pieces, adding actions or triggers, or fixing bugs in existing ones.

    25k GitHub stars~3.1k tokensUpdated today
    Productivity & AutomationAuto-check: notes

More from coddy-project/coddy-agent

  • Crossreview

    coddy-project/coddy-agent

    Run when the user invokes /crossreview (or /crossreview:setup to choose the reviewers) or asks for a cross-review, a quorum review or a second opinion from other agents or models: fan a code review…

    168 GitHub stars~3.3k tokensUpdated today
    Auto-check passed
  • Rpa Init

    coddy-project/coddy-agent

    Run when the user invokes /rpa-init or asks to onboard or warm up context on a repository.

    168 GitHub stars~728 tokensUpdated today
    Auto-check passed
  • Configure Coddy

    coddy-project/coddy-agent

    Change Coddy's own configuration when the user asks for it: edit settings, providers, models, logging, permissions, or find, install, update, and remove MCP servers and skills.

    168 GitHub stars~7.7k tokensUpdated today
    Auto-check: notes
  • Rpa Bugfix

    coddy-project/coddy-agent

    Run when the user invokes /rpa-bugfix together with a clear bug description (expected vs actual, reproduction).

    168 GitHub stars~324 tokensUpdated today
    Auto-check passed
  • Rpa Feat

    coddy-project/coddy-agent

    Run when the user invokes /rpa-feat together with a clear feature description (for example issue text).

    168 GitHub stars~407 tokensUpdated today
    Auto-check passed

Questions about Rpa Gen Rules

What does Rpa Gen Rules do?

A skill your agent uses when the user invokes /rpa-gen-rules or asks to create, refresh, audit, or synchronize project instructions such as root AGENTS.md, Cursor .cursor/rules, or Claude Code…. Rpa Gen Rules is an agent skill from coddy-project/coddy-agent.claude/rules, especially when existing rule trees have drifted.

When should I use Rpa Gen Rules?

Rpa Gen Rules fits situations like: the user invokes /rpa-gen-rules; synchronize project instructions such as root AGENTS.md; Cursor .cursor/rules; Claude Code .claude/rules.

How do I install Rpa Gen Rules in Claude Code?

Run `npx skills add coddy-project/coddy-agent --skill rpa-gen-rules -a claude-code`. Or copy the skill folder (internal/skills/bundled/rpa-gen-rules in coddy-project/coddy-agent) into .claude/skills/rpa-gen-rules in your project. Claude Code loads it when a task matches its description.

How do I install Rpa Gen Rules in Codex?

Run `npx skills add coddy-project/coddy-agent --skill rpa-gen-rules -a codex`. Or copy the skill folder (internal/skills/bundled/rpa-gen-rules in coddy-project/coddy-agent) into .agents/skills/rpa-gen-rules in your project. Codex loads it when a task matches its description.

Can I use Rpa Gen Rules in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add coddy-project/coddy-agent --skill rpa-gen-rules -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/rpa-gen-rules, .gemini/skills/rpa-gen-rules, .github/skills/rpa-gen-rules and .opencode/skills/rpa-gen-rules in your project.

What does Rpa Gen Rules need to run?

Going by SKILL.md and its folder, Rpa Gen Rules needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Rpa Gen Rules access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Rpa Gen Rules safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Rpa Gen Rules use?

Rpa Gen Rules is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Rpa Gen Rules use?

About 1.2k tokens (SKILL.md is roughly 4.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 14k tokens, read only when the agent opens those files.

What are the alternatives to Rpa Gen Rules?

Skills that share tags, products or a category with Rpa Gen Rules: Warp Factory Files (warpdotdev/warp, 65k stars), Fastgpt Workflow Generator (YYH211/Claude-meta-skill, 282 stars), Browser4 Plugin (platonai/Browser4, 1.2k stars) and Lindy Core Workflow B (jeremylongshore/tons-of-skills-marketplace, 2.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Rpa Gen Rules?

coddy-project (a GitHub organization) maintains it in coddy-project/coddy-agent, which has 168 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on October 11, 2026.

Source: coddy-project/coddy-agent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.