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 commands/matthewsuttles/rubyn-code/rubyngit clone --depth 1 https://github.com/MatthewSuttles/rubyn-codeWhat 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 | $0.00000 | $0.01198 |
| Opus 5 | $0.00000 | $0.00599 |
| Sonnet 5 | $0.00000 | $0.00240 |
| Haiku 4.5 | $0.00000 | $0.00120 |
Grade A, and why
RUBYN 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLI::Commands — Slash Command System
Registry-based command dispatch for the REPL. Same Base/Registry pattern as the tool system.
Architecture
User types /help
↓
InputHandler.classify → :command
↓
REPL#handle_command
↓
Registry#dispatch('/help', args, context)
↓
Help#execute(args, context)
↓
(optional) → action hash back to REPL for state changes
Core Infrastructure
| File | Class | Purpose |
|---|---|---|
base.rb |
Base |
Abstract command — command_name, description, aliases, execute(args, ctx) |
registry.rb |
Registry |
Discovers, registers, dispatches commands. Provides tab-completion list |
context.rb |
Context |
Data.define value object with all deps a command needs |
Context Object
Context is a frozen Data.define carrying everything a command might need:
Context = Data.define(
:renderer, :conversation, :agent_loop, :context_manager,
:budget_enforcer, :llm_client, :db, :session_id,
:project_root, :skill_loader, :session_persistence,
:background_worker, :permission_tier, :plan_mode
)
Commands receive it as the second argument to execute. Never mutate it — use
with_message_handler to attach a message callback if the command needs to send
prompts back to the agent loop.
Commands
| Command | File | Description |
|---|---|---|
/budget |
budget.rb |
Show or set session budget (/budget [amount]) |
/clear |
clear.rb |
Clear the terminal |
/compact |
compact.rb |
Compress conversation context |
/context |
context_info.rb |
Show context window usage |
/cost |
cost.rb |
Show token usage and costs |
/diff |
diff.rb |
Show git diff (staged, unstaged, or vs branch) |
/doctor |
doctor.rb |
Environment health check |
/help |
help.rb |
Show this help message |
/model |
model.rb |
Show or switch model (/model [name]) |
/plan |
plan.rb |
Toggle plan mode (think before acting) |
/quit |
quit.rb |
Exit Rubyn Code (aliases: /exit, /q) |
/resume |
resume.rb |
Resume a session or list recent sessions |
/review |
review.rb |
Review current branch against best practices |
/skill |
skill.rb |
Load a skill or list available skills |
/spawn |
spawn.rb |
Spawn a teammate agent (/spawn <name> [role]) |
/tasks |
tasks.rb |
List all tasks |
/tokens |
tokens.rb |
Show token usage and context window estimate |
/undo |
undo.rb |
Remove last exchange |
/version |
version.rb |
Show version info |
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 · 134 lines · 0 tokens per session scan A 0686d2596342
RUBYN is a command published in the GitHub repository MatthewSuttles/rubyn-code (63 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,198 tokens. 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.