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.
npx agentmods add instructions/slbug/claude-ruby-grape-rails/copilot-instructionsgit clone --depth 1 https://github.com/slbug/claude-ruby-grape-railsWhat 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 | $0.03226 | $0.03226 |
| Opus 5 | $0.01613 | $0.01613 |
| Sonnet 5 | $0.00645 | $0.00645 |
| Haiku 4.5 | $0.00323 | $0.00323 |
Grade A, and why
claude-ruby-grape-rails copilot-instructions.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.
How it starts
The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Context
Claude Code plugin for Ruby/Rails/Grape development — NOT a Ruby application. Do NOT suggest Ruby app patterns (controllers, models, routes) for plugin files.
Audience: Agents, Not Humans
All prose in this repo (except README.md, CHANGELOG.md, executable
code under scripts/ / lab/eval/) loads into agent context at runtime:
| Surface | Audience |
|---|---|
| shipped plugin docs | Claude sub-/main-sessions |
.claude/rules/ + .claude/skills/ |
contributor-session Claude |
.github/copilot-instructions.md + .github/instructions/* |
Copilot |
Authoring rules:
- Imperative instructions, not explanatory guides
- No tutorial narration ("first do X, then Y, this teaches…")
- No reasoning preludes — state the action
- No
#thinking/checklist lines inside Bash command bodies (preference #6); use markdown tables / prose around bash blocks to label commands - Markdown tables for option/command lists
PR review: flag prose that violates this rule.
Architecture
| Component | Path | Role |
|---|---|---|
| Agents | plugins/ruby-grape-rails/agents/*.md |
Markdown + YAML frontmatter; specialist reviewers, analyze without modifying |
| Skills | plugins/ruby-grape-rails/skills/*/SKILL.md |
Command-driven or auto-loaded knowledge with references/ subdirs |
| Hooks | plugins/ruby-grape-rails/hooks/hooks.json + scripts/* |
Shell + Ruby triggered by CC events (PostToolUse, PostToolUseFailure, SessionStart, etc) |
| Executables | plugins/ruby-grape-rails/bin/* |
Plugin CLIs added to Bash PATH; no extension; chmod +x; mixed bash + Ruby |
| Library | plugins/ruby-grape-rails/lib/*.rb |
End-user runtime modules (Ruby ≥ 3.4, stdlib only) |
| Plugin settings | plugins/ruby-grape-rails/settings.json |
Only agent + subagentStatusLine keys supported per CC docs |
| Eval | lab/eval/ |
Deterministic Python eval framework for plugin quality |
| Contributor tooling | .claude/ |
NOT shipped; .claude/rules/ (auto-loaded path-scoped rules), .claude/skills/ (contributor-only skills) |
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.
- 2d ago First seen · 227 lines · 3,226 tokens per session scan A 1bac5c8e55b9
claude-ruby-grape-rails copilot-instructions.md is an instructions file published in the GitHub repository slbug/claude-ruby-grape-rails (7 stars, last pushed 3d ago), licensed MIT. It adds 3,226 tokens to every session, about $0.0161 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.
Other instructions, from other repositories
claude-ruby-marketplace CLAUDE.md
Instructions for hoblin/claude-ruby-marketplace, covering claude.md, repository purpose, before editing, directory structure and versioning.
goai AGENTS.md
Instructions for zendev-sh/goai, covering agents.md - goai, commands, architecture, key rules and adding providers.
bifrost AGENTS.md
Instructions for bifrost-proxy/bifrost, covering bifrost 项目开发规则, 执行心法, 执行模式与完成定义, 任务模式判定 and 变更类型与验证路由（先判定，后执行）.
mnemon AGENTS.md
Instructions for mnemon-dev/mnemon, covering mnemon agent guidelines, development, go engineering and commit discipline.
calva-backseat-driver copilot-instructions.md
Instructions for BetterThanTomorrow/calva-backseat-driver, covering what backseat driver is, repl environment, state inspection safety, bundled ai context (chatskills / chatinstructions) and key development commands.
neo4j-ruby-driver CLAUDE.md
Instructions for neo4jrb/neo4j-ruby-driver, covering neo4j ruby driver, branches, essential references, specifications and official drivers (for comparison).