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 skills add tzachbon/smart-ralph --skill ralph-specum-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/skills/tzachbon/smart-ralph/ralph-specum-help)<a href="https://agentmods.dev/skills/tzachbon/smart-ralph/ralph-specum-help"><img src="https://agentmods.dev/badge/skills/tzachbon/smart-ralph/ralph-specum-help/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tzachbon/smart-ralph/ralph-specum-help"><img src="https://agentmods.dev/badge/skills/tzachbon/smart-ralph/ralph-specum-help.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00041 | $0.00767 |
| Opus 5 | $0.00020 | $0.00383 |
| Sonnet 5 | $0.00008 | $0.00153 |
| Haiku 4.5 | $0.00004 | $0.00077 |
Grade A, and why
ralph-specum-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 9d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ralph Specum Help
Use this to explain the Ralph Specum surface in Codex.
Cover
- Primary skill:
$ralph-specum - Helper skills:
$ralph-specum-start,$ralph-specum-triage,$ralph-specum-research,$ralph-specum-requirements,$ralph-specum-design,$ralph-specum-tasks,$ralph-specum-prototype,$ralph-specum-implement,$ralph-specum-status,$ralph-specum-switch,$ralph-specum-cancel,$ralph-specum-index,$ralph-specum-refactor,$ralph-specum-feedback,$ralph-specum-help - Normal flow: start goal grill, approval, research, artifact approval, requirements grill, approval, design grill, approval, tasks grill, approval, implement
- Large effort flow: triage, then start each unblocked spec
- Quick mode: only exact
--quickbypasses interview questions; exact--interactiveclears it. Discovery, skill loads, and artifact write gates still run - Disk contract:
./specsor configured roots,.current-spec, optional.current-epic, per-spec markdown files,.ralph-state.json
Optional Prototype Overlay
- Direct mode: invoke
$ralph-specum-prototypefrom research, requirements, design, tasks, or execution. Preserve the main phase and current checkout. - Suggested mode: research or requirements may offer
continue to prototype, then return to the next normal phase. - Resume mode: use
$ralph-specum-prototype --resume <id>. One active entry resumes automatically; several are listed deterministically for selection. - Quick mode: run exactly one agent-owned request after requirements, ask no prototype questions, take over the oldest design blocker or select the highest-risk grounded, falsifiable question when no blocker exists, own verdict and handoff decisions, and continue to design for every result.
- Cancel mode: use
$ralph-specum-prototype --cancel <id>or safe spec cancellation. Stop at a safe boundary, publish a reviewed immutablecancelledrecord, and preserve source and partial implementation.
Store terminal records under the resolved <basePath>/prototypes/. Run source work in a sibling worktree or eligible scratch area without switching the current checkout or copying unapproved dirty paths. Keep source, evidence, records, and branches local. Require separate authorization for every push, PR or issue change, and other remote action. Require exact-path and local-branch confirmation before local deletion; never delete a remote branch during prototype cleanup.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 41 lines · 41 tokens per session scan A 0577d826cbb6
ralph-specum-help is a skill published in the GitHub repository tzachbon/smart-ralph (537 stars, last pushed 6d ago), licensed MIT. It adds 41 tokens to every session and 767 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
remember
Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs.
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.
explaining-machine-learning-models
Explain trained machine learning models through feature attribution, local explanations, and behavior summaries. Use as an explicit/manual helper once a model already exists, not for training ownership, leakage auditing, or general ML strategy selection.
config-validator
Validate AIWG configuration files and project setup for correctness and completeness.
aiwg-regenerate-copilot
Regenerate copilot-instructions.md for GitHub Copilot with vendor-specific content only.
steward-prep-delivery
Steward-assisted prep for filing issues and PRs — environment capture, template selection, duplicate detection, delivery-policy compliance check.