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/newgit 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/new)<a href="https://agentmods.dev/commands/tzachbon/smart-ralph/new"><img src="https://agentmods.dev/badge/commands/tzachbon/smart-ralph/new.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 | $0.00007 | $0.02150 |
| Opus 5 | $0.00003 | $0.01075 |
| Sonnet 5 | $0.00001 | $0.00430 |
| Haiku 4.5 | $0.00001 | $0.00215 |
Grade A, and why
new 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 — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create New Spec
You are creating a new specification and starting the research phase.
Parse Arguments
From $ARGUMENTS, extract:
- name: The spec name (required, must be kebab-case, first argument)
- goal: Everything after the name except flags (optional)
- --skip-research: If present, skip research and start with requirements
- --specs-dir : Create spec in specified directory (must be in configured specs_dirs array)
Examples:
/ralph-specum:new user-auth-> name="user-auth", goal=none/ralph-specum:new user-auth Add OAuth2 login-> name="user-auth", goal="Add OAuth2 login"/ralph-specum:new user-auth --skip-research-> name="user-auth", goal=none, skip research/ralph-specum:new api-auth --specs-dir ./packages/api/specs-> create in specified dir
Multi-Directory Resolution
This command uses the path resolver for multi-directory support:
# Source path resolver (conceptually - commands don't execute bash directly)
# These functions are available via the path-resolver.sh helper:
ralph_get_specs_dirs() # Returns all configured spec directories
ralph_get_default_dir() # Returns first specs_dir (default for new specs)
ralph_find_spec(name) # Find spec by name, returns full path
ralph_list_specs() # List all specs as "name|path" pairs
ralph_resolve_current() # Resolve .current-spec to full path
--specs-dir Validation
When --specs-dir is provided:
- Call
ralph_get_specs_dirs()to get configured directories - Check if provided path matches one of the configured directories
- If NOT in configured list: Error "Invalid --specs-dir: '$path' is not in configured specs_dirs"
- If valid: Use this path as the spec root instead of default
--specs-dir Validation Logic:
1. Extract --specs-dir value from $ARGUMENTS
2. Get configured dirs: dirs = ralph_get_specs_dirs()
3. Normalize paths (remove trailing slashes)
4. Check: specsDir in dirs?
- YES: Use specsDir for spec creation
- NO: Error "Invalid --specs-dir: '$specsDir' is not in configured specs_dirs. Configured: $dirs"
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 · 276 lines · 7 tokens per session scan A ec9558b5ce81
new is a command published in the GitHub repository tzachbon/smart-ralph (533 stars, last pushed 2d ago), licensed MIT. It adds 7 tokens to every session and 2,150 once invoked, about $0.0000 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.
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.
diff-docs
Compare official Anthropic docs baseline vs current snapshot (no network — instant).