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/tzachbon/smart-ralph/helpgit clone --depth 1 https://github.com/tzachbon/smart-ralphWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/tzachbon/smart-ralph/help)<a href="https://agentmods.dev/commands/tzachbon/smart-ralph/help"><img src="https://agentmods.dev/badge/commands/tzachbon/smart-ralph/help.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00011 | $0.02171 |
| Opus 5 | $0.00005 | $0.01086 |
| Sonnet 5 | $0.00002 | $0.00434 |
| Haiku 4.5 | $0.00001 | $0.00217 |
Grade A, and why
help 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 yesterday.
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 — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ralph Specum Help
Overview
Ralph Specum is a spec-driven development plugin that guides you through research, requirements, design, and task generation phases, then executes tasks autonomously with fresh context per task.
Commands
| Command | Description |
|---|---|
/ralph-specum:start [name] [goal] |
Smart entry point: resume or create new |
/ralph-specum:new <name> [goal] |
Create new spec and start research |
/ralph-specum:research |
Run/re-run research phase |
/ralph-specum:requirements |
Generate requirements (approves research) |
/ralph-specum:design |
Generate design (approves requirements) |
/ralph-specum:tasks |
Generate tasks (approves design) |
/ralph-specum:prototype [--resume ID | --cancel ID | --quick] |
Run, resume, or cancel optional prototype evidence |
/ralph-specum:implement |
Start execution loop (approves tasks) |
/ralph-specum:status |
Show all specs and progress |
/ralph-specum:switch <name> |
Change active spec |
/ralph-specum:cancel |
Safely cancel active work; source is preserved |
/ralph-specum:feedback [message] |
Submit feedback or report an issue |
/ralph-specum:help |
Show this help |
Workflow
/ralph-specum:new "my-feature"
|
v
[Research Phase] - Automatic on new
|
v (review research.md)
/ralph-specum:requirements
|
v (review requirements.md)
/ralph-specum:design
|
v (review design.md)
/ralph-specum:tasks
|
v (review tasks.md)
/ralph-specum:implement
|
v
[Task-by-task execution with fresh context]
|
v
Done!
Quick Start
# Easiest: use start (auto-detects resume or new)
/ralph-specum:start user-auth Add JWT authentication
# Or resume an existing spec
/ralph-specum:start
# Manual workflow with individual commands:
/ralph-specum:new user-auth Add JWT authentication
/ralph-specum:requirements
/ralph-specum:design
/ralph-specum:tasks
/ralph-specum:implement
Optional Prototype Overlay
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.
- yesterday First seen · 256 lines · 11 tokens per session scan A ade4c00291a1
help is a command published in the GitHub repository tzachbon/smart-ralph (533 stars, last pushed 2d ago), licensed MIT. It adds 11 tokens to every session and 2,171 once invoked, about $0.0001 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 2026-09-03.
Other commands, from other repositories
psm
/oh-my-claudecode:psm is a compatibility alias for /oh-my-claudecode:project-session-manager.
project
Generate project documentation (product.md, structure.md, tech.md, codemaps/).
version
Display current guide and Claude Code versions.
discover
Run a full product discovery cycle — from outcome definition through opportunity mapping, prioritisation, and experiment design. Use when the team isn't sure what to build next, or before writing a PRD for a complex feature space.
diff-docs
Compare official Anthropic docs baseline vs current snapshot (no network — instant).
voice-compliance
Voice/telephony compliance check — invokes voice-ai-reviewer to produce TM-voice-{slug}.md with TCPA, STIR/SHAKEN, state recording-consent, EU AI Act Art. 50, and synth-voice deepfake-law gaps.