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 witt3rd/oh-my-hermes --skill omh-ralplan-drivergit clone --depth 1 https://github.com/witt3rd/oh-my-hermesWrote 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/witt3rd/oh-my-hermes/omh-ralplan-driver)<a href="https://agentmods.dev/skills/witt3rd/oh-my-hermes/omh-ralplan-driver"><img src="https://agentmods.dev/badge/skills/witt3rd/oh-my-hermes/omh-ralplan-driver/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/witt3rd/oh-my-hermes/omh-ralplan-driver"><img src="https://agentmods.dev/badge/skills/witt3rd/oh-my-hermes/omh-ralplan-driver.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 | $0.00021 | $0.12856 |
| Opus 5 | $0.00010 | $0.06428 |
| Sonnet 5 | $0.00004 | $0.02571 |
| Haiku 4.5 | $0.00002 | $0.01286 |
Grade A, and why
omh-ralplan-driver 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 11d 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 — 1,250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OMH Ralplan Driver — driving the loop
Load this skill alongside omh-ralplan when you are the orchestrator
dispatching the loop. omh-ralplan is loaded by the Planner / Architect
/ Critic workers — it covers what they do inside each delegate_task
call. This skill covers what you do as the dispatcher: prep, dispatch,
distill, review.
The two skills have different readers and different jobs. Don't merge them — worker context is precious; the dispatcher's playbook should not ride into every subagent.
Why this skill exists
Ralplan without disciplined orchestration converges on internal consistency, not truth. The Planner / Architect / Critic triangle is self-checking — it will produce a coherent stance about whatever you pointed it at, including the wrong frame, the stale source, the phantom constraint, and the question the user already settled.
The orchestrator is the only role with the vantage to:
- Carve principles before dispatching.
- Author a context package that licenses framing contests.
- Verify ground truth and adjacent mechanisms before subagents inherit them as fact.
- Iterate the package with the user — half of any non-trivial requirements come from the user's lived context, not from reading.
- Distill consensus into a canonical artifact stripped of reviewer scaffolding.
- Apply a final quality gate before handing anything to the user.
Most of the failure modes named below are pre-dispatch failures. Prep is where quality is born. Distillation and review preserve it. The loop itself is just the well-instrumented engine in between.
When to use ralplan vs just think
Use ralplan when the work has:
- Multiple legitimate decompositions of the problem.
- Load-bearing principles that need enforcing across subagents.
- Cross-cutting concerns the orchestrator might miss alone.
- A user who would otherwise be in a turn-by-turn proposal loop.
Don't use ralplan when the work is single-file, single-decision, or
obvious-to-solve. Overkill is its own failure mode. Use
omh-deep-interview first if the goal is ambiguous.
What ships with it
5 files 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.
- 11d ago First seen · 1,250 lines · 21 tokens per session scan A 4f4e90bd50d7
omh-ralplan-driver is a skill published in the GitHub repository witt3rd/oh-my-hermes (322 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 12,856 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 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.