ruly CLAUDE.md

Project instructions for the Ruly repository, covering how to maintain its rules, recipes, commands, skills, and integrations with MCP servers. MCP is a standard way for an agent to connect to external tools.

In plain words
What is it for?
Use them when changing Ruly rules, slash commands, recipes, MCP settings, or skills, including updating required documentation and references.
Why use it?
They keep repository changes consistent and prevent edits to generated files or related configuration from being missed.

Instructions file

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 instructions/patrickclery/ruly/claude-md
Clone the repo
git clone --depth 1 https://github.com/patrickclery/ruly
Per session 1,093 This file is loaded in full into every session.
When invoked 1,093 The same file — it is already loaded in full.
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 $0.01093 $0.01093
Opus 5 $0.00547 $0.00547
Sonnet 5 $0.00219 $0.00219
Haiku 4.5 $0.00109 $0.00109

Measured 2d ago against content hash 57d2ac489e48, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ruly CLAUDE.md 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 2d 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.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

  • always update the ~/.config/ruly/recipes.yml and /Users/patrick/Projects/chezmoi/config/ruly/recipes.yml when you change things it references (they should be identical)
  • Every time the slash commands are updated, make sure to update the slash command section of README.md
  • When changing ruly CLI commands (squash, clean, analyze, mcp, etc.), always update README.md to reflect the changes
  • NEVER edit CLAUDE.local.md — it is generated output from ruly squash and will be overwritten. Fix the source rules in ./rules/ instead.
  • When I ask to change rules, don't change the rules in .claude/ always look in ./rules/
  • When I ask to create a skill, add it to rules/{tag}/skills/{skill-name}.md (Ruly searches for skills in that structure)
  • Skills in rules/ are regular .md files, NOT SKILL.md - Ruly converts them to SKILL.md format on squash
  • Always use git mv to move/rename files instead of deleting and re-creating them (preserves git history)
  • When deleting/moving/renaming files in rules/, always search for references to update:
    • requires: frontmatter in other rule files
    • Recipe files (recipes.yml, ~/.config/ruly/recipes.yml)
    • Section anchor links that may have changed
  • When I say "commit" or "commit all", commit and push ALL modified files in BOTH repos (don't assume any changes are unrelated):
    1. The rules submodule (./rules) → https://github.com/patrickclery/rules
    2. The parent ruly repo → https://github.com/patrickclery/ruly (update submodule reference)
  • Always use Mermaid for diagrams/flowcharts in rules (never graphviz/dot). Exception: Jira/Confluence don't support Mermaid, so use ASCII diagrams there instead.

Claude Code Instructions

Ruly Recipe and MCP Configuration Patterns

Import Ruly recipe configuration patterns and MCP server guidelines. @./.claude/ruly-recipes-mcp-patterns.md

  • When testing out ruly squash ..., always run it from a mktmpdir and not the main project directory
  • always update ruly after any changes. for instance, /Users/patrick/.local/share/mise/installs/ruby/3.3.3/bin/ruly is out of sync right now
  • Whenever you want token counts for recipes, run ruly stats and read the results from stats.md
  • After any changes to the core recipe (either recipes.yml or any file it references), run: cd ~/agents/core && ruly squash --deepclean core. Do this before ending the session — check whether any file you modified is referenced by the core recipe.

Read the full file on GitHub · 93 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. 2d ago First seen · 93 lines · 1,093 tokens per session scan A 57d2ac489e48

Subscribe to this mod's changes

ruly CLAUDE.md is an instructions file published in the GitHub repository patrickclery/ruly (5 stars, last pushed 7d ago), licensed MIT. It adds 1,093 tokens to every session, about $0.0055 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 2026-08-31.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens