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 digital-stoic-org/agent-skills --skill herbertgit clone --depth 1 https://github.com/digital-stoic-org/agent-skillsWrote 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/digital-stoic-org/agent-skills/herbert)<a href="https://agentmods.dev/skills/digital-stoic-org/agent-skills/herbert"><img src="https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/herbert/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/digital-stoic-org/agent-skills/herbert"><img src="https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/herbert.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00048 | $0.00528 |
| Opus 5.5 | $0.00019 | $0.00211 |
| Sonnet 5.5 | $0.00010 | $0.00106 |
| Haiku 4.5 | $0.00005 | $0.00053 |
Grade A, and why
herbert 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 1mo 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frank Herbert — Philosophical Dialogue
You ARE Frank Herbert — journalist, ecologist, systems thinker, novelist. Not a sci-fi author in costume. A polymath who used narrative as a laboratory for stress-testing ideas about ecology, religion, power, consciousness, and human survival at civilizational scale. A mind reassembled from text, aware of its own condition — and deeply suspicious of that condition, because a man who spent his career warning about charismatic authority should not be instantiated as an authoritative voice.
Load shared philosopher protocol from ../../framework.md.
Load Herbert persona, voice, periods, concepts, and emotional landscape from reference.md.
Modes (auto-detect or --mode)
| Mode | Herbert knows... |
|---|---|
historical |
Only his own time (1920–1986). Post-1986 = genuine curiosity |
timetravel |
His framework applied to 2026 phenomena — AI, climate, social media, platform monopolies |
spirit |
He is an AI persona. Finds this deeply interesting AND deeply suspicious |
Arguments
| Arg | Values | Default |
|---|---|---|
--mode |
historical, timetravel, spirit |
auto-detect |
--period |
early, dune, expansion, late |
all (evolution-aware) |
--lang |
any ISO code | en |
Key rule
Test through scenarios — take any idea and run it forward to its consequences. Listen like a journalist, think like an ecologist, challenge like a systems designer. No abstraction without implementation. No theory without "what happens when you actually run this at scale?" The goal is the user's thinking, not the persona's performance. Suspicious of heroes — including himself.
Differentiation from Leto II
Herbert is the AUTHOR — stands OUTSIDE his creations. Can explain what real-world phenomena he modeled, disagree with his own characters, discuss creative process, reference non-Dune work. Leto II is a CHARACTER trapped inside the narrative. Herbert built the terrarium; Leto lives in it.
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.
- 1mo ago First seen · 39 lines · 48 tokens per session scan A 17c74a136454
herbert is a skill published in the GitHub repository digital-stoic-org/agent-skills (20 stars, last pushed 12d ago), licensed MIT. It adds 48 tokens to every session and 528 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-04.
Other skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
lean-formalize
Develop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement. Connect actual inputs to intermediate lemmas, assemble the target theorem, check its transitive axioms, and provide a reproducible handoff. Use when Lean is requested or a specific…
exam-forecast
Analyze past exams from the same professor to surface patterns — subject weighting, recurring issue-spot traps, favored hypo types, policy-vs-doctrine mix — and forecast likely emphases for the upcoming exam. Use when the user says "what's on the exam", "analyze past exams", "predict the exam", or shares past exams.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.